SherbyNet - /page/wikibook/entry.mu

Micron Document

<!DOCTYPE html>

<title>Feature engineering</title>

</head>

Feature engineering

</h1>

</header>

/* start https://en.wikipedia.org/ */

.mw-parser-output .hlist dl,.mw-parser-output .hlist ol,.mw-parser-output .hlist ul{margin:0;padding:0}.mw-parser-output .hlist dd,.mw-parser-output .hlist dt,.mw-parser-output .hlist li{margin:0;display:inline}.mw-parser-output .hlist.inline,.mw-parser-output .hlist.inline dl,.mw-parser-output .hlist.inline ol,.mw-parser-output .hlist.inline ul,.mw-parser-output .hlist dl dl,.mw-parser-output .hlist dl ol,.mw-parser-output .hlist dl ul,.mw-parser-output .hlist ol dl,.mw-parser-output .hlist ol ol,.mw-parser-output .hlist ol ul,.mw-parser-output .hlist ul dl,.mw-parser-output .hlist ul ol,.mw-parser-output .hlist ul ul{display:inline}.mw-parser-output .hlist .mw-empty-li{display:none}.mw-parser-output .hlist dt::after{content:": "}.mw-parser-output .hlist dd::after,.mw-parser-output .hlist li::after{content:" · ";font-weight:bold}.mw-parser-output .hlist dd:last-child::after,.mw-parser-output .hlist dt:last-child::after,.mw-parser-output .hlist li:last-child::after{content:none}.mw-parser-output .hlist dd dd:first-child::before,.mw-parser-output .hlist dd dt:first-child::before,.mw-parser-output .hlist dd li:first-child::before,.mw-parser-output .hlist dt dd:first-child::before,.mw-parser-output .hlist dt dt:first-child::before,.mw-parser-output .hlist dt li:first-child::before,.mw-parser-output .hlist li dd:first-child::before,.mw-parser-output .hlist li dt:first-child::before,.mw-parser-output .hlist li li:first-child::before{content:" (";font-weight:normal}.mw-parser-output .hlist dd dd:last-child::after,.mw-parser-output .hlist dd dt:last-child::after,.mw-parser-output .hlist dd li:last-child::after,.mw-parser-output .hlist dt dd:last-child::after,.mw-parser-output .hlist dt dt:last-child::after,.mw-parser-output .hlist dt li:last-child::after,.mw-parser-output .hlist li dd:last-child::after,.mw-parser-output .hlist li dt:last-child::after,.mw-parser-output .hlist li li:last-child::after{content:")";font-weight:normal}.mw-parser-output .hlist ol{counter-reset:listitem}.mw-parser-output .hlist ol>li{counter-increment:listitem}.mw-parser-output .hlist ol>li::before{content:" "counter(listitem)"\a0 "}.mw-parser-output .hlist dd ol>li:first-child::before,.mw-parser-output .hlist dt ol>li:first-child::before,.mw-parser-output .hlist li ol>li:first-child::before{content:" ("counter(listitem)"\a0 "}

/* end https://en.wikipedia.org/ */

</style><style data-mw-deduplicate="TemplateStyles:r1246091330">

/* start https://en.wikipedia.org/ */

.mw-parser-output .sidebar{width:22em;float:right;clear:right;margin:0.5em 0 1em 1em;background:var(--background-color-neutral-subtle,#f8f9fa);border:1px solid var(--border-color-base,#a2a9b1);padding:0.2em;text-align:center;line-height:1.4em;font-size:88%;border-collapse:collapse;display:table}body.skin-minerva .mw-parser-output .sidebar{display:table!important;float:right!important;margin:0.5em 0 1em 1em!important}.mw-parser-output .sidebar-subgroup{width:100%;margin:0;border-spacing:0}.mw-parser-output .sidebar-left{float:left;clear:left;margin:0.5em 1em 1em 0}.mw-parser-output .sidebar-none{float:none;clear:both;margin:0.5em 1em 1em 0}.mw-parser-output .sidebar-outer-title{padding:0 0.4em 0.2em;font-size:125%;line-height:1.2em;font-weight:bold}.mw-parser-output .sidebar-top-image{padding:0.4em}.mw-parser-output .sidebar-top-caption,.mw-parser-output .sidebar-pretitle-with-top-image,.mw-parser-output .sidebar-caption{padding:0.2em 0.4em 0;line-height:1.2em}.mw-parser-output .sidebar-pretitle{padding:0.4em 0.4em 0;line-height:1.2em}.mw-parser-output .sidebar-title,.mw-parser-output .sidebar-title-with-pretitle{padding:0.2em 0.8em;font-size:145%;line-height:1.2em}.mw-parser-output .sidebar-title-with-pretitle{padding:0.1em 0.4em}.mw-parser-output .sidebar-image{padding:0.2em 0.4em 0.4em}.mw-parser-output .sidebar-heading{padding:0.1em 0.4em}.mw-parser-output .sidebar-content{padding:0 0.5em 0.4em}.mw-parser-output .sidebar-content-with-subgroup{padding:0.1em 0.4em 0.2em}.mw-parser-output .sidebar-above,.mw-parser-output .sidebar-below{padding:0.3em 0.8em;font-weight:bold}.mw-parser-output .sidebar-collapse .sidebar-above,.mw-parser-output .sidebar-collapse .sidebar-below{border-top:1px solid #aaa;border-bottom:1px solid #aaa}.mw-parser-output .sidebar-navbar{text-align:right;font-size:115%;padding:0 0.4em 0.4em}.mw-parser-output .sidebar-list-title{padding:0 0.4em;text-align:left;font-weight:bold;line-height:1.6em;font-size:105%}.mw-parser-output .sidebar-list-title-c{padding:0 0.4em;text-align:center;margin:0 3.3em}@media(max-width:640px){body.mediawiki .mw-parser-output .sidebar{width:100%!important;clear:both;float:none!important;margin-left:0!important;margin-right:0!important}}body.skin--responsive .mw-parser-output .sidebar a>img{max-width:none!important}@media screen{html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-list-title,html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle{background:transparent!important}html.skin-theme-clientpref-night .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle a{color:var(--color-progressive)!important}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-list-title,html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle{background:transparent!important}html.skin-theme-clientpref-os .mw-parser-output .sidebar:not(.notheme) .sidebar-title-with-pretitle a{color:var(--color-progressive)!important}}@media print{body.ns-0 .mw-parser-output .sidebar{display:none!important}}

/* end https://en.wikipedia.org/ */

</style><style data-mw-deduplicate="TemplateStyles:r886047488">

/* start https://en.wikipedia.org/ */

.mw-parser-output .nobold{font-weight:normal}

/* end https://en.wikipedia.org/ */

</style><table class="sidebar sidebar-collapse nomobile nowraplinks"><tbody><tr><td class="sidebar-pretitle">Part of a series on</td></tr><tr><th class="sidebar-title-with-pretitle"><a href="Machine_learning" title="Machine learning">Machine learning</a> and <a href="Data_mining" title="Data mining">data mining</a></th></tr><tr><td class="sidebar-content">

<ul><li><a href="Supervised_learning" title="Supervised learning">Supervised learning</a></li>

<li><a href="Unsupervised_learning" title="Unsupervised learning">Unsupervised learning</a></li>

<li><a href="Semi-supervised_learning" class="mw-redirect" title="Semi-supervised learning">Semi-supervised learning</a></li>

<li><a href="Self-supervised_learning" title="Self-supervised learning">Self-supervised learning</a></li>

<li><a href="Reinforcement_learning" title="Reinforcement learning">Reinforcement learning</a></li>

<li><a href="Meta-learning_(computer_science)" title="Meta-learning (computer science)">Meta-learning</a></li>

<li><a href="Online_machine_learning" title="Online machine learning">Online learning</a></li>

<li><a href="Batch_learning" class="mw-redirect" title="Batch learning">Batch learning</a></li>

<li><a href="Curriculum_learning" title="Curriculum learning">Curriculum learning</a></li>

<li><a href="Rule-based_machine_learning" title="Rule-based machine learning">Rule-based learning</a></li>

<li><a href="Neuro-symbolic_AI" title="Neuro-symbolic AI">Neuro-symbolic AI</a></li>

<li><a href="Neuromorphic_engineering" class="mw-redirect" title="Neuromorphic engineering">Neuromorphic engineering</a></li>

<li><a href="Quantum_machine_learning" title="Quantum machine learning">Quantum machine learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)">Problems</div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Statistical_classification" title="Statistical classification">Classification</a></li>

<li><a href="Generative_model" title="Generative model">Generative modeling</a></li>

<li><a href="Regression_analysis" title="Regression analysis">Regression</a></li>

<li><a href="Cluster_analysis" title="Cluster analysis">Clustering</a></li>

<li><a href="Dimensionality_reduction" title="Dimensionality reduction">Dimensionality reduction</a></li>

<li><a href="Density_estimation" title="Density estimation">Density estimation</a></li>

<li><a href="Anomaly_detection" title="Anomaly detection">Anomaly detection</a></li>

<li><a href="Data_cleaning" class="mw-redirect" title="Data cleaning">Data cleaning</a></li>

<li><a href="Automated_machine_learning" title="Automated machine learning">AutoML</a></li>

<li><a href="Association_rule_learning" title="Association rule learning">Association rules</a></li>

<li><a href="Semantic_analysis_(machine_learning)" title="Semantic analysis (machine learning)">Semantic analysis</a></li>

<li><a href="Structured_prediction" title="Structured prediction">Structured prediction</a></li>

<li><a href="Feature_learning" title="Feature learning">Feature learning</a></li>

<li><a href="Learning_to_rank" title="Learning to rank">Learning to rank</a></li>

<li><a href="Grammar_induction" title="Grammar induction">Grammar induction</a></li>

<li><a href="Ontology_learning" title="Ontology learning">Ontology learning</a></li>

<li><a href="Multimodal_learning" title="Multimodal learning">Multimodal learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><div style="display: inline-block; line-height: 1.2em; padding: .1em 0;"><a href="Supervised_learning" title="Supervised learning">Supervised learning</a> (<a href="Statistical_classification" title="Statistical classification">classification</a> • <a href="Regression_analysis" title="Regression analysis">regression</a>) </div></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Apprenticeship_learning" title="Apprenticeship learning">Apprenticeship learning</a></li>

<li><a href="Decision_tree_learning" title="Decision tree learning">Decision trees</a></li>

<li><a href="Ensemble_learning" title="Ensemble learning">Ensembles</a>

<ul><li><a href="Bootstrap_aggregating" title="Bootstrap aggregating">Bagging</a></li>

<li><a href="Boosting_(machine_learning)" title="Boosting (machine learning)">Boosting</a></li>

<li><a href="Random_forest" title="Random forest">Random forest</a></li></ul></li>

<li><a href="Linear_regression" title="Linear regression">Linear regression</a></li>

<li><a href="Naive_Bayes_classifier" title="Naive Bayes classifier">Naive Bayes</a></li>

<li><a href="Artificial_neural_network" class="mw-redirect" title="Artificial neural network">Artificial neural networks</a></li>

<li><a href="Logistic_regression" title="Logistic regression">Logistic regression</a></li>

<li><a href="Perceptron" title="Perceptron">Perceptron</a></li>

<li><a href="Relevance_vector_machine" title="Relevance vector machine">Relevance vector machine (RVM)</a></li>

<li><a href="Support_vector_machine" title="Support vector machine">Support vector machine (SVM)</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Cluster_analysis" title="Cluster analysis">Clustering</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="BIRCH" title="BIRCH">BIRCH</a></li>

<li><a href="Hierarchical_clustering" title="Hierarchical clustering">Hierarchical</a></li>

<li><a href="K-means_clustering" title="K-means clustering">k-means</a></li>

<li><a href="Fuzzy_clustering" title="Fuzzy clustering">Fuzzy</a></li>

<li><a href="Expectation%E2%80%93maximization_algorithm" title="Expectation–maximization algorithm">Expectation–maximization (EM)</a></li>

<li> <a href="DBSCAN" title="DBSCAN">DBSCAN</a></li>

<li><a href="OPTICS_algorithm" title="OPTICS algorithm">OPTICS</a></li>

<li><a href="Mean_shift" title="Mean shift">Mean shift</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Dimensionality_reduction" title="Dimensionality reduction">Dimensionality reduction</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Factor_analysis" title="Factor analysis">Factor analysis</a></li>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Structured_prediction" title="Structured prediction">Structured prediction</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Graphical_model" title="Graphical model">Graphical models</a>

<ul><li><a href="Bayesian_network" title="Bayesian network">Bayes net</a></li>

<li><a href="Conditional_random_field" title="Conditional random field">Conditional random field</a></li>

<li><a href="Hidden_Markov_model" title="Hidden Markov model">Hidden Markov</a></li></ul></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Anomaly_detection" title="Anomaly detection">Anomaly detection</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Random_sample_consensus" title="Random sample consensus">RANSAC</a></li>

<li><a href="Local_outlier_factor" title="Local outlier factor">Local outlier factor</a></li>

<li><a href="Isolation_forest" title="Isolation forest">Isolation forest</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Neural_network_(machine_learning)" title="Neural network (machine learning)">Neural networks</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Autoencoder" title="Autoencoder">Autoencoder</a></li>

<li><a href="Deep_learning" title="Deep learning">Deep learning</a></li>

<li><a href="Feedforward_neural_network" title="Feedforward neural network">Feedforward neural network</a></li>

<li><a href="Recurrent_neural_network" title="Recurrent neural network">Recurrent neural network</a>

<li><a href="Reservoir_computing" title="Reservoir computing">reservoir computing</a></li></ul></li>

<li><a href="Boltzmann_machine" title="Boltzmann machine">Boltzmann machine</a>

<ul><li><a href="Restricted_Boltzmann_machine" title="Restricted Boltzmann machine">Restricted</a></li></ul></li>

<li><a href="Diffusion_model" title="Diffusion model">Diffusion model</a></li>

<li><a href="Convolutional_neural_network" title="Convolutional neural network">Convolutional neural network</a>

<li><a href="LeNet" title="LeNet">LeNet</a></li>

<li><a href="AlexNet" title="AlexNet">AlexNet</a></li>

<li><a href="DeepDream" title="DeepDream">DeepDream</a></li></ul></li>

<li><a href="Neural_field" title="Neural field">Neural field</a>

<ul><li><a href="Neural_radiance_field" title="Neural radiance field">Neural radiance field</a></li>

<li><a href="Physics-informed_neural_networks" title="Physics-informed neural networks">Physics-informed neural networks</a></li></ul></li>

<li><a href="Transformer_(deep_learning_architecture)" title="Transformer (deep learning architecture)">Transformer</a>

<ul><li><a href="Vision_transformer" title="Vision transformer">Vision</a></li></ul></li>

<li><a href="Mamba_(deep_learning_architecture)" title="Mamba (deep learning architecture)">Mamba</a></li>

<li><a href="Spiking_neural_network" title="Spiking neural network">Spiking neural network</a></li>

<li><a href="Memtransistor" title="Memtransistor">Memtransistor</a></li>

<li><a href="Electrochemical_RAM" title="Electrochemical RAM">Electrochemical RAM</a> (ECRAM)</li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)"><a href="Reinforcement_learning" title="Reinforcement learning">Reinforcement learning</a></div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Q-learning" title="Q-learning">Q-learning</a></li>

<li><a href="Policy_gradient_method" title="Policy gradient method">Policy gradient</a></li>

<li><a href="State%E2%80%93action%E2%80%93reward%E2%80%93state%E2%80%93action" title="State–action–reward–state–action">SARSA</a></li>

<li><a href="Temporal_difference_learning" title="Temporal difference learning">Temporal difference (TD)</a></li>

<li><a href="Multi-agent_reinforcement_learning" title="Multi-agent reinforcement learning">Multi-agent</a>

</tr><tr><td class="sidebar-content">

<ul><li><a href="Active_learning_(machine_learning)" title="Active learning (machine learning)">Active learning</a></li>

<li><a href="Crowdsourcing" title="Crowdsourcing">Crowdsourcing</a></li>

<li><a href="Human-in-the-loop" title="Human-in-the-loop">Human-in-the-loop</a></li>

<li><a href="Mechanistic_interpretability" title="Mechanistic interpretability">Mechanistic interpretability</a></li>

</tr><tr><td class="sidebar-content">

<ul><li><a href="Coefficient_of_determination" title="Coefficient of determination">Coefficient of determination</a></li>

<li><a href="Confusion_matrix" title="Confusion matrix">Confusion matrix</a></li>

<li><a href="Learning_curve_(machine_learning)" title="Learning curve (machine learning)">Learning curve</a></li>

<li><a href="Receiver_operating_characteristic" title="Receiver operating characteristic">ROC curve</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)">Mathematical foundations</div><div class="sidebar-list-content mw-collapsible-content hlist">

<ul><li><a href="Kernel_machines" class="mw-redirect" title="Kernel machines">Kernel machines</a></li>

<li><a href="Bias%E2%80%93variance_tradeoff" title="Bias–variance tradeoff">Bias–variance tradeoff</a></li>

<li><a href="Computational_learning_theory" title="Computational learning theory">Computational learning theory</a></li>

<li><a href="Empirical_risk_minimization" title="Empirical risk minimization">Empirical risk minimization</a></li>

<li><a href="Occam_learning" title="Occam learning">Occam learning</a></li>

<li><a href="Probably_approximately_correct_learning" title="Probably approximately correct learning">PAC learning</a></li>

<li><a href="Statistical_learning_theory" title="Statistical learning theory">Statistical learning</a></li>

<li><a href="Vapnik%E2%80%93Chervonenkis_theory" title="Vapnik–Chervonenkis theory">VC theory</a></li>

<li><a href="Topological_deep_learning" title="Topological deep learning">Topological deep learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-content">

<div class="sidebar-list mw-collapsible mw-collapsed machine-learning-list-title"><div class="sidebar-list-title" style="border-top:1px solid #aaa; text-align:center;;color: var(--color-base)">Journals and conferences</div><div class="sidebar-list-content mw-collapsible-content hlist">

<li><a href="Conference_on_Neural_Information_Processing_Systems" title="Conference on Neural Information Processing Systems">NeurIPS</a></li>

<li><a href="International_Joint_Conference_on_Artificial_Intelligence" title="International Joint Conference on Artificial Intelligence">IJCAI</a></li>

</tr><tr><td class="sidebar-content">

<ul><li><a href="Glossary_of_artificial_intelligence" title="Glossary of artificial intelligence">Glossary of artificial intelligence</a></li>

<li><a href="List_of_datasets_for_machine-learning_research" title="List of datasets for machine-learning research">List of datasets for machine-learning research</a>

<ul><li><a href="List_of_datasets_in_computer_vision_and_image_processing" title="List of datasets in computer vision and image processing">List of datasets in computer vision and image processing</a></li></ul></li>

<li><a href="Outline_of_machine_learning" title="Outline of machine learning">Outline of machine learning</a></li></ul></div></div></td>

</tr><tr><td class="sidebar-navbar"><style data-mw-deduplicate="TemplateStyles:r1239400231">

/* start https://en.wikipedia.org/ */

.mw-parser-output .navbar{display:inline;font-size:88%;font-weight:normal}.mw-parser-output .navbar-collapse{float:left;text-align:left}.mw-parser-output .navbar-boxtext{word-spacing:0}.mw-parser-output .navbar ul{display:inline-block;white-space:nowrap;line-height:inherit}.mw-parser-output .navbar-brackets::before{margin-right:-0.125em;content:"[ "}.mw-parser-output .navbar-brackets::after{margin-left:-0.125em;content:" ]"}.mw-parser-output .navbar li{word-spacing:-0.125em}.mw-parser-output .navbar a>span,.mw-parser-output .navbar a>abbr{text-decoration:inherit}.mw-parser-output .navbar-mini abbr{font-variant:small-caps;border-bottom:none;text-decoration:none;cursor:inherit}.mw-parser-output .navbar-ct-full{font-size:114%;margin:0 7em}.mw-parser-output .navbar-ct-mini{font-size:114%;margin:0 4em}html.skin-theme-clientpref-night .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}@media(prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .navbar li a abbr{color:var(--color-base)!important}}@media print{.mw-parser-output .navbar{display:none!important}}

/* end https://en.wikipedia.org/ */

</style></td></tr></tbody></table><style data-mw-deduplicate="TemplateStyles:r1305433154">

/* start https://en.wikipedia.org/ */

.mw-parser-output .ambox{border:1px solid #a2a9b1;border-left:10px solid #36c;background-color:#fbfbfb;box-sizing:border-box}.mw-parser-output .ambox+link+.ambox,.mw-parser-output .ambox+link+style+.ambox,.mw-parser-output .ambox+link+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+style+.ambox,.mw-parser-output .ambox+.mw-empty-elt+link+link+.ambox{margin-top:-1px}html body.mediawiki .mw-parser-output .ambox.mbox-small-left{margin:4px 1em 4px 0;overflow:hidden;width:238px;border-collapse:collapse;font-size:88%;line-height:1.25em}.mw-parser-output .ambox-speedy{border-left:10px solid #b32424;background-color:#fee7e6}.mw-parser-output .ambox-delete{border-left:10px solid #b32424}.mw-parser-output .ambox-content{border-left:10px solid #f28500}.mw-parser-output .ambox-style{border-left:10px solid #fc3}.mw-parser-output .ambox-move{border-left:10px solid #9932cc}.mw-parser-output .ambox-protection{border-left:10px solid #a2a9b1}.mw-parser-output .ambox .mbox-text{border:none;padding:0.25em 0.5em;width:100%}.mw-parser-output .ambox .mbox-image{border:none;padding:2px 0 2px 0.5em;text-align:center}.mw-parser-output .ambox .mbox-imageright{border:none;padding:2px 0.5em 2px 0;text-align:center}.mw-parser-output .ambox .mbox-empty-cell{border:none;padding:0;width:1px}.mw-parser-output .ambox .mbox-image-div{width:52px}@media(min-width:720px){.mw-parser-output .ambox{margin:0 10%}}@media print{body.ns-0 .mw-parser-output .ambox{display:none!important}}

/* end https://en.wikipedia.org/ */

</style>

Feature engineering is a preprocessing step in <a href="Supervised_machine_learning" class="mw-redirect" title="Supervised machine learning">supervised machine learning</a> and <a href="Statistical_modeling" class="mw-redirect" title="Statistical modeling">statistical modeling</a><a href="#cite_note-1">[1]</a> which transforms raw data into a more effective set of inputs. Each input comprises several attributes, known as features. By providing models with relevant information, feature engineering significantly enhances their predictive accuracy and decision-making capability.<a href="#cite_note-auto1-2">[2]</a><a href="#cite_note-3">[3]</a><a href="#cite_note-4">[4]</a>

Beyond machine learning, the principles of feature engineering are applied in various scientific fields, including physics. For example, physicists construct <a href="Dimensionless_quantity" title="Dimensionless quantity">dimensionless numbers</a> such as the <a href="Reynolds_number" title="Reynolds number">Reynolds number</a> in <a href="Fluid_dynamics" title="Fluid dynamics">fluid dynamics</a>, the <a href="Nusselt_number" title="Nusselt number">Nusselt number</a> in <a href="Heat_transfer" title="Heat transfer">heat transfer</a>, and the <a href="Archimedes_number" title="Archimedes number">Archimedes number</a> in <a href="Sedimentation" title="Sedimentation">sedimentation</a>. They also develop first approximations of solutions, such as analytical solutions for the <a href="Strength_of_materials" title="Strength of materials">strength of materials</a> in mechanics.<a href="#cite_note-5">[5]</a>

<div class="mw-heading mw-heading2"><h2 id="Clustering">Clustering</h2></div>

One of the applications of feature engineering has been clustering of feature-objects or sample-objects in a dataset. Especially, feature engineering based on <a href="Matrix_decomposition" title="Matrix decomposition">matrix decomposition</a> has been extensively used for data clustering under non-negativity constraints on the feature coefficients. These include Non-Negative Matrix Factorization (NMF),<a href="#cite_note-6">[6]</a> Non-Negative Matrix-Tri Factorization (NMTF),<a href="#cite_note-7">[7]</a> Non-Negative Tensor Decomposition/Factorization (NTF/NTD),<a href="#cite_note-8">[8]</a> etc. The non-negativity constraints on coefficients of the feature vectors mined by the above-stated algorithms yields a part-based representation, and different factor matrices exhibit natural clustering properties. Several extensions of the above-stated feature engineering methods have been reported in literature, including orthogonality-constrained factorization for hard clustering, and manifold learning to overcome inherent issues with these algorithms.

Other classes of feature engineering algorithms include leveraging a common hidden structure across multiple inter-related datasets to obtain a consensus (common) clustering scheme. An example is Multi-view Classification based on Consensus Matrix Decomposition (MCMD),<a href="#cite_note-auto1-2">[2]</a> which mines a common clustering scheme across multiple datasets. MCMD is designed to output two types of class labels (scale-variant and scale-invariant clustering), and:

<ul><li>is <a href="Robustness_(computer_science)" title="Robustness (computer science)">computationally robust</a> to missing information,</li>

<li>can obtain shape- and scale-based outliers,</li>

<li>and can handle high-dimensional data effectively.</li></ul>

Coupled matrix and tensor decompositions are popular in multi-view feature engineering.<a href="#cite_note-9">[9]</a>

<div class="mw-heading mw-heading2"><h2 id="Predictive_modelling">Predictive modelling</h2></div>

Feature engineering in <a href="Machine_learning" title="Machine learning">machine learning</a> and <a href="Statistical_modeling" class="mw-redirect" title="Statistical modeling">statistical modeling</a> involves selecting, creating, transforming, and extracting data features. Key components include feature creation from existing data, transforming and imputing missing or invalid features, reducing data dimensionality through methods like <a href="Principal_component_analysis" title="Principal component analysis">Principal Components Analysis</a> (PCA), <a href="Independent_component_analysis" title="Independent component analysis">Independent Component Analysis</a> (ICA), and <a href="Linear_discriminant_analysis" title="Linear discriminant analysis">Linear Discriminant Analysis</a> (LDA), and selecting the most relevant features for model training based on importance scores and <a href="Correlation_matrices" class="mw-redirect" title="Correlation matrices">correlation matrices</a>.<a href="#cite_note-10">[10]</a>

Features vary in significance.<a href="#cite_note-11">[11]</a> Even relatively insignificant features may contribute to a model. <a href="Feature_selection" title="Feature selection">Feature selection</a> can reduce the number of features to prevent a model from becoming too specific to the training data set (overfitting).<a href="#cite_note-12">[12]</a>

Feature explosion occurs when the number of identified features is too large for effective model estimation or optimization. Common causes include:

<ul><li>Feature templates - implementing feature templates instead of coding new features</li>

<li>Feature combinations - combinations that cannot be represented by a linear system</li></ul>

Feature explosion can be limited via techniques such as: <a href="Regularization_(mathematics)" title="Regularization (mathematics)">regularization</a>, <a href="Kernel_method" title="Kernel method">kernel methods</a>, and <a href="Feature_selection" title="Feature selection">feature selection</a>.<a href="#cite_note-13">[13]</a>

<div class="mw-heading mw-heading2"><h2 id="Automation">Automation</h2></div>

Automation of feature engineering is a research topic that dates back to the 1990s.<a href="#cite_note-:0-14">[14]</a> Machine learning software that incorporates <a href="Automated_feature_engineering" class="mw-redirect" title="Automated feature engineering">automated feature engineering</a> has been commercially available since 2016.<a href="#cite_note-15">[15]</a> Related academic literature can be roughly separated into two types:

<ul><li>Multi-relational decision tree learning (MRDTL) uses a supervised algorithm that is similar to a <a href="Decision_tree" title="Decision tree">decision tree</a>.</li>

<li>Deep Feature Synthesis uses simpler methods.</li></ul>

<div class="mw-heading mw-heading3"><h3 id="Multi-relational_decision_tree_learning_(MRDTL)">Multi-relational decision tree learning (MRDTL)</h3></div>

Multi-relational Decision Tree Learning (MRDTL) extends traditional decision tree methods to <a href="Relational_database" title="Relational database">relational databases</a>, handling complex data relationships across tables. It innovatively uses selection graphs as <a href="Decision_node" class="mw-redirect" title="Decision node">decision nodes</a>, refined systematically until a specific termination criterion is reached.<a href="#cite_note-:0-14">[14]</a>

Most MRDTL studies base implementations on relational databases, which results in many redundant operations. These redundancies can be reduced by using techniques such as tuple id propagation.<a href="#cite_note-16">[16]</a><a href="#cite_note-17">[17]</a>

<div class="mw-heading mw-heading3"><h3 id="Open-source_implementations">Open-source implementations</h3></div>

There are a number of open-source libraries and tools that automate feature engineering on relational data and time series:

<ul><li>featuretools is a <a href="Python_(programming_language)" title="Python (programming language)">Python</a> library for transforming time series and relational data into feature matrices for machine learning.<a href="#cite_note-18">[18]</a><a href="#cite_note-19">[19]</a><a href="#cite_note-20">[20]</a></li>

<li>MCMD: An open-source feature engineering algorithm for joint clustering of multiple datasets . <a href="#cite_note-21">[21]</a><a href="#cite_note-auto1-2">[2]</a></li>

<li>OneBM or One-Button Machine combines feature transformations and feature selection on relational data with feature selection techniques.<a href="#cite_note-auto2-22">[22]</a> <style data-mw-deduplicate="TemplateStyles:r1244412712">

/* start https://en.wikipedia.org/ */

.mw-parser-output .templatequote{overflow:hidden;margin:1em 0;padding:0 32px}.mw-parser-output .templatequotecite{line-height:1.5em;text-align:left;margin-top:0}@media(min-width:500px){.mw-parser-output .templatequotecite{padding-left:1.6em}}

/* end https://en.wikipedia.org/ */

</style><blockquote class="templatequote">[OneBM] helps data scientists reduce data exploration time allowing them to try and error many ideas in short time. On the other hand, it enables non-experts, who are not familiar with data science, to quickly extract value from their data with a little effort, time, and cost.<a href="#cite_note-auto2-22">[22]</a></blockquote></li>

<li>getML community is an open source tool for automated feature engineering on time series and relational data.<a href="#cite_note-23">[23]</a><a href="#cite_note-auto-24">[24]</a> It is implemented in <a href="C_(programming_language)" title="C (programming language)">C</a>/<a href="C%2B%2B" title="C++">C++</a> with a Python interface.<a href="#cite_note-auto-24">[24]</a> It has been shown to be at least 60 times faster than tsflex, tsfresh, tsfel, featuretools or kats.<a href="#cite_note-auto-24">[24]</a></li>

<li>tsfresh is a Python library for feature extraction on time series data.<a href="#cite_note-25">[25]</a> It evaluates the quality of the features using hypothesis testing.<a href="#cite_note-26">[26]</a></li>

<li>tsflex is an open source Python library for extracting features from time series data.<a href="#cite_note-27">[27]</a> Despite being 100% written in Python, it has been shown to be faster and more memory efficient than tsfresh, seglearn or tsfel.<a href="#cite_note-28">[28]</a></li>

<li>seglearn is an extension for multivariate, sequential time series data to the <a href="Scikit-learn" title="Scikit-learn">scikit-learn</a> Python library.<a href="#cite_note-29">[29]</a></li>

<li>tsfel is a Python package for feature extraction on time series data.<a href="#cite_note-30">[30]</a></li>

<li>kats is a Python toolkit for analyzing time series data.<a href="#cite_note-31">[31]</a></li></ul>

<div class="mw-heading mw-heading3"><h3 id="Deep_feature_synthesis">Deep feature synthesis</h3></div>

The deep feature synthesis (DFS) algorithm beat 615 of 906 human teams in a competition.<a href="#cite_note-32">[32]</a><a href="#cite_note-33">[33]</a>

<div class="mw-heading mw-heading2"><h2 id="Feature_stores">Feature stores</h2></div>

The feature store is where the features are stored and organized for the explicit purpose of being used to either train models (by data scientists) or make predictions (by applications that have a trained model). It is a central location where you can either create or update groups of features created from multiple different data sources, or create and update new datasets from those feature groups for training models or for use in applications that do not want to compute the features but just retrieve them when it needs them to make predictions.<a href="#cite_note-34">[34]</a>

A feature store includes the ability to store code used to generate features, apply the code to raw data, and serve those features to models upon request. Useful capabilities include feature versioning and policies governing the circumstances under which features can be used.<a href="#cite_note-35">[35]</a>

Feature stores can be standalone software tools or built into machine learning platforms.

<div class="mw-heading mw-heading2"><h2 id="Alternatives">Alternatives</h2></div>

Feature engineering can be a time-consuming and error-prone process, as it requires domain expertise and often involves trial and error.<a href="#cite_note-36">[36]</a><a href="#cite_note-37">[37]</a> <a href="Deep_learning" title="Deep learning">Deep learning algorithms</a> may be used to process a large raw dataset without having to resort to feature engineering.<a href="#cite_note-38">[38]</a> However, deep learning algorithms still require careful preprocessing and cleaning of the input data.<a href="#cite_note-39">[39]</a> In addition, choosing the right architecture, hyperparameters, and optimization algorithm for a deep neural network can be a challenging and iterative process.<a href="#cite_note-40">[40]</a>

<ul><li><a href="Covariate" class="mw-redirect" title="Covariate">Covariate</a></li>

<li><a href="Data_transformation_(statistics)" title="Data transformation (statistics)">Data transformation</a></li>

<li><a href="Feature_extraction" class="mw-redirect" title="Feature extraction">Feature extraction</a></li>

<li><a href="Feature_learning" title="Feature learning">Feature learning</a></li>

<li><a href="Hashing_trick" class="mw-redirect" title="Hashing trick">Hashing trick</a></li>

<li><a href="Instrumental_variables_estimation" title="Instrumental variables estimation">Instrumental variables estimation</a></li>

<li><a href="Kernel_method" title="Kernel method">Kernel method</a></li>

<li><a href="List_of_datasets_for_machine_learning_research" class="mw-redirect" title="List of datasets for machine learning research">List of datasets for machine learning research</a></li>

<li><a href="Scale_co-occurrence_matrix" title="Scale co-occurrence matrix">Scale co-occurrence matrix</a></li>

<li><a href="Space_mapping" title="Space mapping">Space mapping</a></li></ul>

<div class="mw-heading mw-heading2"><h2 id="References">References</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .reflist{margin-bottom:0.5em;list-style-type:decimal}@media screen{.mw-parser-output .reflist{font-size:90%}}.mw-parser-output .reflist .references{font-size:100%;margin-bottom:0;list-style-type:inherit}.mw-parser-output .reflist-columns-2{column-width:30em}.mw-parser-output .reflist-columns-3{column-width:25em}.mw-parser-output .reflist-columns{margin-top:0.3em}.mw-parser-output .reflist-columns ol{margin-top:0}.mw-parser-output .reflist-columns li{page-break-inside:avoid;break-inside:avoid-column}.mw-parser-output .reflist-upper-alpha{list-style-type:upper-alpha}.mw-parser-output .reflist-upper-roman{list-style-type:upper-roman}.mw-parser-output .reflist-lower-alpha{list-style-type:lower-alpha}.mw-parser-output .reflist-lower-greek{list-style-type:lower-greek}.mw-parser-output .reflist-lower-roman{list-style-type:lower-roman}

/* end https://en.wikipedia.org/ */

</style><div class="reflist">

/* start https://en.wikipedia.org/ */

.mw-parser-output cite.citation{font-style:inherit;word-wrap:break-word}.mw-parser-output .citation q{quotes:"\"""\"""'""'"}.mw-parser-output .citation:target{background-color:rgba(0,127,255,0.133)}.mw-parser-output .id-lock-free.id-lock-free a{background:url("./mw/Lock-green.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-limited.id-lock-limited a,.mw-parser-output .id-lock-registration.id-lock-registration a{background:url("./mw/Lock-gray-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .id-lock-subscription.id-lock-subscription a{background:url("./mw/Lock-red-alt-2.svg")right 0.1em center/9px no-repeat}.mw-parser-output .cs1-ws-icon a{background:url("./mw/Wikisource-logo.svg")right 0.1em center/12px no-repeat}body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-free a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-limited a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-registration a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .id-lock-subscription a,body:not(.skin-timeless):not(.skin-minerva) .mw-parser-output .cs1-ws-icon a{background-size:contain;padding:0 1em 0 0}.mw-parser-output .cs1-code{color:inherit;background:inherit;border:none;padding:inherit}.mw-parser-output .cs1-hidden-error{display:none;color:var(--color-error,#d33)}.mw-parser-output .cs1-visible-error{color:var(--color-error,#d33)}.mw-parser-output .cs1-maint{display:none;color:#085;margin-left:0.3em}.mw-parser-output .cs1-kern-left{padding-left:0.2em}.mw-parser-output .cs1-kern-right{padding-right:0.2em}.mw-parser-output .citation .mw-selflink{font-weight:inherit}@media screen{.mw-parser-output .cs1-format{font-size:95%}html.skin-theme-clientpref-night .mw-parser-output .cs1-maint{color:#18911f}}@media screen and (prefers-color-scheme:dark){html.skin-theme-clientpref-os .mw-parser-output .cs1-maint{color:#18911f}}

/* end https://en.wikipedia.org/ */

</style><cite id="CITEREFHastieTibshiraniFriedman2009" class="citation book cs1">Hastie, Trevor; Tibshirani, Robert; Friedman, Jerome H. (2009). <a rel="nofollow" class="external text" href="https://books.google.com/books?id=eBSgoAEACAAJ">The Elements of Statistical Learning: Data Mining, Inference, and Prediction</a>. Springer. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-0-387-84884-6</bdi>.</cite>

</li>

<li id="cite_note-auto1-2">^ <a href="#cite_ref-auto1_2-0">a</a> <a href="#cite_ref-auto1_2-1">b</a> <a href="#cite_ref-auto1_2-2">c</a> <cite id="CITEREFSharmaNayakBhaskar2024" class="citation journal cs1">Sharma, Shubham; Nayak, Richi; Bhaskar, Ashish (2024-05-01). <a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.trc.2024.104607">"Multi-view feature engineering for day-to-day joint clustering of multiple traffic datasets"</a>. Transportation Research Part C: Emerging Technologies. 162 104607. <a href="Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/2024TRPC..16204607S">2024TRPC..16204607S</a>. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.trc.2024.104607">10.1016/j.trc.2024.104607</a>. <a href="ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/0968-090X">0968-090X</a>.</cite>

</li>

<li id="cite_note-3"><a href="#cite_ref-3">^</a> <cite id="CITEREFShalev-ShwartzBen-David2014" class="citation book cs1">Shalev-Shwartz, Shai; Ben-David, Shai (2014). Understanding Machine Learning: From Theory to Algorithms. Cambridge: Cambridge University Press. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9781107057135</bdi>.</cite>

</li>

<li id="cite_note-4"><a href="#cite_ref-4">^</a> <cite id="CITEREFMurphy2022" class="citation book cs1">Murphy, Kevin P. (2022). Probabilistic Machine Learning. Cambridge, Massachusetts: The MIT Press (Copyright 2022 Massachusetts Institute of Technology, this work is subject to a Creative Commons CC-BY-NC-ND license). <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>9780262046824</bdi>.</cite>

</li>

<li id="cite_note-5"><a href="#cite_ref-5">^</a> <cite id="CITEREFMacQueron2021" class="citation report cs1">MacQueron C (2021). <a rel="nofollow" class="external text" href="https://www.researchgate.net/publication/353947052">SOLID-LIQUID MIXING IN STIRRED TANKS : Modeling, Validation, Design Optimization and Suspension Quality Prediction</a> (Report). <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.13140%2FRG.2.2.11074.84164%2F1">10.13140/RG.2.2.11074.84164/1</a>.</cite>

</li>

<li id="cite_note-6"><a href="#cite_ref-6">^</a> <cite id="CITEREFLeeSeung1999" class="citation journal cs1">Lee, Daniel D.; Seung, H. Sebastian (1999). <a rel="nofollow" class="external text" href="https://www.nature.com/articles/44565">"Learning the parts of objects by non-negative matrix factorization"</a>. Nature. 401 (6755): 788–791. <a href="Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/1999Natur.401..788L">1999Natur.401..788L</a>. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1038%2F44565">10.1038/44565</a>. <a href="ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1476-4687">1476-4687</a>. <a href="PMID_(identifier)" class="mw-redirect" title="PMID (identifier)">PMID</a> <a rel="nofollow" class="external text" href="https://pubmed.ncbi.nlm.nih.gov/10548103">10548103</a>.</cite>

</li>

<li id="cite_note-7"><a href="#cite_ref-7">^</a> <cite id="CITEREFWangNieHuangDing2011" class="citation book cs1">Wang, Hua; Nie, Feiping; Huang, Heng; Ding, Chris (2011). <a rel="nofollow" class="external text" href="https://dx.doi.org/10.1109/icdm.2011.109">"Nonnegative Matrix Tri-factorization Based High-Order Co-clustering and Its Fast Implementation"</a>. 2011 IEEE 11th International Conference on Data Mining. IEEE. pp. 774–783. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2Ficdm.2011.109">10.1109/icdm.2011.109</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-1-4577-2075-8</bdi>.</cite>

</li>

<li id="cite_note-8"><a href="#cite_ref-8">^</a> <cite id="CITEREFLimComon2009" class="citation arxiv cs1">Lim, Lek-Heng; Comon, Pierre (2009-04-12). "Nonnegative approximations of nonnegative tensors". <a href="ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<a rel="nofollow" class="external text" href="https://arxiv.org/abs/0903.4530">0903.4530</a> [<a rel="nofollow" class="external text" href="https://arxiv.org/archive/cs.NA">cs.NA</a>].</cite>

</li>

<li id="cite_note-9"><a href="#cite_ref-9">^</a> <cite id="CITEREFNayakLuong2023" class="citation journal cs1">Nayak, Richi; Luong, Khanh (2023). <a rel="nofollow" class="external text" href="https://doi.org/10.1007/978-3-031-33560-0">"Multi-aspect Learning"</a>. Intelligent Systems Reference Library. 242. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2F978-3-031-33560-0">10.1007/978-3-031-33560-0</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-3-031-33559-4</bdi>. <a href="ISSN_(identifier)" class="mw-redirect" title="ISSN (identifier)">ISSN</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/issn/1868-4394">1868-4394</a>.</cite>

</li>

<li id="cite_note-10"><a href="#cite_ref-10">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://docs.aws.amazon.com/wellarchitected/latest/machine-learning-lens/feature-engineering.html">"Feature engineering - Machine Learning Lens"</a>. docs.aws.amazon.com. Retrieved 2024-03-01.</cite>

</li>

<li id="cite_note-11"><a href="#cite_ref-11">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.cs.princeton.edu/courses/archive/spring10/cos424/slides/18-feat.pdf">"Feature Engineering"</a> (PDF). 2010-04-22. Retrieved 12 November 2015.</cite>

</li>

<li id="cite_note-12"><a href="#cite_ref-12">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="http://www.cs.berkeley.edu/~jordan/courses/294-fall09/lectures/feature/slides.pdf">"Feature engineering and selection"</a> (PDF). Alexandre Bouchard-Côté. October 1, 2009. Retrieved 12 November 2015.</cite>

</li>

<li id="cite_note-13"><a href="#cite_ref-13">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20160304112056/https://ufal.mff.cuni.cz/~zabokrtsky/courses/npfl104/html/feature_engineering.pdf">"Feature engineering in Machine Learning"</a> (PDF). Zdenek Zabokrtsky. Archived from <a rel="nofollow" class="external text" href="https://ufal.mff.cuni.cz/~zabokrtsky/courses/npfl104/html/feature_engineering.pdf">the original</a> (PDF) on 4 March 2016. Retrieved 12 November 2015.</cite>

</li>

<li id="cite_note-:0-14">^ <a href="#cite_ref-:0_14-0">a</a> <a href="#cite_ref-:0_14-1">b</a> <cite id="CITEREFKnobbeSiebesVan_Der_Wallen1999" class="citation book cs1">Knobbe AJ, Siebes A, Van Der Wallen D (1999). <a rel="nofollow" class="external text" href="https://link.springer.com/content/pdf/10.1007/978-3-540-48247-5_46.pdf">"Multi-relational Decision Tree Induction"</a> (PDF). Principles of Data Mining and Knowledge Discovery. Lecture Notes in Computer Science. Vol. 1704. pp. 378–383. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2F978-3-540-48247-5_46">10.1007/978-3-540-48247-5_46</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-3-540-66490-1</bdi>.</cite>

</li>

<li id="cite_note-15"><a href="#cite_ref-15">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://reality.ai/it-is-all-about-the-features/">"Its all about the features"</a>. Reality AI Blog. September 2017.</cite>

</li>

<li id="cite_note-16"><a href="#cite_ref-16">^</a> <cite id="CITEREFYinHanYangYu2004" class="citation book cs1">Yin X, Han J, Yang J, Yu PS (2004). "CrossMine: Efficient classification across multiple database relations". Proceedings. 20th International Conference on Data Engineering. pp. 399–410. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FICDE.2004.1320014">10.1109/ICDE.2004.1320014</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>0-7695-2065-0</bdi>. <a href="S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:1183403">1183403</a>.</cite>

</li>

<li id="cite_note-17"><a href="#cite_ref-17">^</a> <cite id="CITEREFFrankMoserEster2007" class="citation book cs1">Frank R, Moser F, Ester M (2007). "A Method for Multi-relational Classification Using Single and Multi-feature Aggregation Functions". Knowledge Discovery in Databases: PKDD 2007. Lecture Notes in Computer Science. Vol. 4702. pp. 430–437. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2F978-3-540-74976-9_43">10.1007/978-3-540-74976-9_43</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-3-540-74975-2</bdi>.</cite>

</li>

<li id="cite_note-18"><a href="#cite_ref-18">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://featuretools.alteryx.com/en/stable/">"What is Featuretools?"</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-19"><a href="#cite_ref-19">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://web.archive.org/web/20190818175732/https://www.featuretools.com/">"Featuretools - An open source python framework for automated feature engineering"</a>. Archived from <a rel="nofollow" class="external text" href="https://www.featuretools.com/">the original</a> on August 18, 2019. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-20"><a href="#cite_ref-20">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/alteryx/featuretools">"github: alteryx/featuretools"</a>. <a href="GitHub" title="GitHub">GitHub</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-21"><a href="#cite_ref-21">^</a> <cite id="CITEREFSharma" class="citation cs2">Sharma, Shubham, <a rel="nofollow" class="external text" href="https://github.com/ashishbhaskar/MCMD">mcmd: Multi-view Classification framework based on Consensus Matrix Decomposition developed by Shubham Sharma at QUT</a>, retrieved 2024-04-14</cite>

</li>

<li id="cite_note-auto2-22">^ <a href="#cite_ref-auto2_22-0">a</a> <a href="#cite_ref-auto2_22-1">b</a> <cite id="CITEREFThanh_LamThiebautSinnChen2017" class="citation arxiv cs1">Thanh Lam, Hoang; Thiebaut, Johann-Michael; Sinn, Mathieu; Chen, Bei; Mai, Tiep; Alkan, Oznur (2017-06-01). "One button machine for automating feature engineering in relational databases". <a href="ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<a rel="nofollow" class="external text" href="https://arxiv.org/abs/1706.00327">1706.00327</a> [<a rel="nofollow" class="external text" href="https://arxiv.org/archive/cs.DB">cs.DB</a>].</cite>

</li>

<li id="cite_note-23"><a href="#cite_ref-23">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://docs.getml.com/latest/">"getML documentation"</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-auto-24">^ <a href="#cite_ref-auto_24-0">a</a> <a href="#cite_ref-auto_24-1">b</a> <a href="#cite_ref-auto_24-2">c</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/getml/getml-community">"github: getml/getml-community"</a>. <a href="GitHub" title="GitHub">GitHub</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-25"><a href="#cite_ref-25">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://tsfresh.readthedocs.io/en/latest">"tsfresh documentation"</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-26"><a href="#cite_ref-26">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.researchgate.net/publication/324948288">"Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh – A Python package)"</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-27"><a href="#cite_ref-27">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/predict-idlab/tsflex">"predict-idlab/tsflex"</a>. <a href="GitHub" title="GitHub">GitHub</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-28"><a href="#cite_ref-28">^</a> <cite id="CITEREFVan_Der_DoncktVan_Der_DoncktDeprostVan_Hoecke2022" class="citation journal cs1">Van Der Donckt, Jonas; Van Der Donckt, Jeroen; Deprost, Emiel; Van Hoecke, Sofie (2022). <a rel="nofollow" class="external text" href="https://www.sciencedirect.com/science/article/pii/S2352711021001904">"tsflex: Flexible time series processing & feature extraction"</a>. SoftwareX. 17 100971. <a href="ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<a rel="nofollow" class="external text" href="https://arxiv.org/abs/2111.12429">2111.12429</a>. <a href="Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/2022SoftX..1700971V">2022SoftX..1700971V</a>. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.softx.2021.100971">10.1016/j.softx.2021.100971</a>. <a href="S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:244527198">244527198</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-29"><a href="#cite_ref-29">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://dmbee.github.io/seglearn/user_guide.html">"seglearn user guide"</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-30"><a href="#cite_ref-30">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://tsfel.readthedocs.io/en/latest/">"Welcome to TSFEL documentation!"</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-31"><a href="#cite_ref-31">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://github.com/facebookresearch/Kats">"github: facebookresearch/Kats"</a>. <a href="GitHub" title="GitHub">GitHub</a>. Retrieved September 7, 2022.</cite>

</li>

<li id="cite_note-32"><a href="#cite_ref-32">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://news.mit.edu/2015/automating-big-data-analysis-1016">"Automating big-data analysis"</a>. 16 October 2015.</cite>

</li>

<li id="cite_note-33"><a href="#cite_ref-33">^</a> <cite id="CITEREFKanterVeeramachaneni2015" class="citation book cs1">Kanter, James Max; Veeramachaneni, Kalyan (2015). "Deep feature synthesis: Towards automating data science endeavors". 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA). pp. 1–10. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1109%2FDSAA.2015.7344858">10.1109/DSAA.2015.7344858</a>. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-1-4673-8272-4</bdi>. <a href="S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:206610380">206610380</a>.</cite>

</li>

<li id="cite_note-34"><a href="#cite_ref-34">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.featurestore.org/what-is-a-feature-store">"What is a feature store"</a>. Retrieved 2022-04-19.</cite>

</li>

<li id="cite_note-35"><a href="#cite_ref-35">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://phaseai.com/resources/intro-to-feature-stores">"An Introduction to Feature Stores"</a>. Retrieved 2021-04-15.</cite>

</li>

<li id="cite_note-36"><a href="#cite_ref-36">^</a> <cite class="citation web cs1"><a rel="nofollow" class="external text" href="https://www.section.io/engineering-education/feature-engineering-in-machine-learning/">"Feature Engineering in Machine Learning"</a>. Engineering Education (EngEd) Program | Section. Retrieved 2023-03-21.</cite>

</li>

<li id="cite_note-37"><a href="#cite_ref-37">^</a> <cite id="CITEREFexplorium_admin2021" class="citation web cs1">explorium_admin (2021-10-25). <a rel="nofollow" class="external text" href="https://www.explorium.ai/blog/5-reasons-why-feature-engineering-is-challenging/">"5 Reasons Why Feature Engineering is Challenging"</a>. Explorium. Retrieved 2023-03-21.</cite>

</li>

<li id="cite_note-38"><a href="#cite_ref-38">^</a> <cite id="CITEREFSpiegelhalter2019" class="citation book cs1">Spiegelhalter, D. J. (2019). The art of statistics : learning from data. [London] UK. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-0-241-39863-0</bdi>. <a href="OCLC_(identifier)" class="mw-redirect" title="OCLC (identifier)">OCLC</a> <a rel="nofollow" class="external text" href="https://search.worldcat.org/oclc/1064776283">1064776283</a>.</cite><code class="cs1-code">{{cite book}}</code>: CS1 maint: location missing publisher (link)

</li>

<li id="cite_note-39"><a href="#cite_ref-39">^</a> <cite id="CITEREFSarker2021" class="citation journal cs1">Sarker IH (November 2021). <a rel="nofollow" class="external text" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8372231">"Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions"</a>. SN Computer Science. 2 (6) 420. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2Fs42979-021-00815-1">10.1007/s42979-021-00815-1</a>. <a href="PMC_(identifier)" class="mw-redirect" title="PMC (identifier)">PMC</a> <a rel="nofollow" class="external text" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8372231">8372231</a>. <a href="PMID_(identifier)" class="mw-redirect" title="PMID (identifier)">PMID</a> <a rel="nofollow" class="external text" href="https://pubmed.ncbi.nlm.nih.gov/34426802">34426802</a>.</cite>

</li>

<li id="cite_note-40"><a href="#cite_ref-40">^</a> <cite id="CITEREFBengio2012" class="citation cs2">Bengio, Yoshua (2012), <a rel="nofollow" class="external text" href="https://dx.doi.org/10.1007/978-3-642-35289-8_26">"Practical Recommendations for Gradient-Based Training of Deep Architectures"</a>, Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, vol. 7700, Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 437–478, <a href="ArXiv_(identifier)" class="mw-redirect" title="ArXiv (identifier)">arXiv</a>:<a rel="nofollow" class="external text" href="https://arxiv.org/abs/1206.5533">1206.5533</a>, <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1007%2F978-3-642-35289-8_26">10.1007/978-3-642-35289-8_26</a>, <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-3-642-35288-1</bdi>, <a href="S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:10808461">10808461</a>, retrieved 2023-03-21</cite>

</li>

</ol></div></div>

<div class="mw-heading mw-heading2"><h2 id="Further_reading">Further reading</h2></div>

/* start https://en.wikipedia.org/ */

.mw-parser-output .refbegin{margin-bottom:0.5em}.mw-parser-output .refbegin-hanging-indents>ul{margin-left:0}.mw-parser-output .refbegin-hanging-indents>ul>li{margin-left:0;padding-left:3.2em;text-indent:-3.2em}.mw-parser-output .refbegin-hanging-indents ul,.mw-parser-output .refbegin-hanging-indents ul li{list-style:none}@media(max-width:720px){.mw-parser-output .refbegin-hanging-indents>ul>li{padding-left:1.6em;text-indent:-1.6em}}.mw-parser-output .refbegin-columns{margin-top:0.3em}.mw-parser-output .refbegin-columns ul{margin-top:0}.mw-parser-output .refbegin-columns li{page-break-inside:avoid;break-inside:avoid-column}@media screen{.mw-parser-output .refbegin{font-size:90%}}

/* end https://en.wikipedia.org/ */

</style><div class="refbegin" style="">

<ul><li><cite id="CITEREFBoehmkeGreenwell2019" class="citation book cs1">Boehmke B, Greenwell B (2019). "Feature & Target Engineering". Hands-On Machine Learning with R. Chapman & Hall. pp. 41–75. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-1-138-49568-5</bdi>.</cite></li>

<li><cite id="CITEREFZhengCasari2018" class="citation book cs1">Zheng A, Casari A (2018). Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists. O'Reilly. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-1-4919-5324-2</bdi>.</cite></li>

<li><cite id="CITEREFZumelMount2020" class="citation book cs1">Zumel N, Mount (2020). "Data Engineering and Data Shaping". Practical Data Science with R (2nd ed.). Manning. pp. 113–160. <a href="ISBN_(identifier)" class="mw-redirect" title="ISBN (identifier)">ISBN</a> <bdi>978-1-61729-587-4</bdi>.</cite></li>

<li><cite id="CITEREFAbououf,_M.Singh,_S.Mizouni,_R.Otrok,_H.2024" class="citation cs2 cs1-prop-vanc-accept">Abououf, M., Singh, S., Mizouni, R., Otrok, H. (2024), <a rel="nofollow" class="external text" href="https://dx.doi.org/10.1016/j.iot.2024.101191">"Feature engineering and deep learning-based approach for event detection in Medical Internet of Things (MIoT)"</a>, Internet of Things, 26 101191, Elsevier BV, <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1016%2Fj.iot.2024.101191">10.1016/j.iot.2024.101191</a></cite></li>

<li><cite id="CITEREFChiccoOnetoTavazzi2022" class="citation journal cs1">Chicco D, Oneto L, Tavazzi E (December 2022). <a rel="nofollow" class="external text" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9754225">"Eleven quick tips for data cleaning and feature engineering"</a>. PLOS Computational Biology. 18 (12): e1010718. <a href="Bibcode_(identifier)" class="mw-redirect" title="Bibcode (identifier)">Bibcode</a>:<a rel="nofollow" class="external text" href="https://ui.adsabs.harvard.edu/abs/2022PLSCB..18E0718C">2022PLSCB..18E0718C</a>. <a href="Doi_(identifier)" class="mw-redirect" title="Doi (identifier)">doi</a>:<a rel="nofollow" class="external text" href="https://doi.org/10.1371%2Fjournal.pcbi.1010718">10.1371/journal.pcbi.1010718</a>. <a href="PMC_(identifier)" class="mw-redirect" title="PMC (identifier)">PMC</a> <a rel="nofollow" class="external text" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9754225">9754225</a>. <a href="PMID_(identifier)" class="mw-redirect" title="PMID (identifier)">PMID</a> <a rel="nofollow" class="external text" href="https://pubmed.ncbi.nlm.nih.gov/36520712">36520712</a>. <a href="S2CID_(identifier)" class="mw-redirect" title="S2CID (identifier)">S2CID</a> <a rel="nofollow" class="external text" href="https://api.semanticscholar.org/CorpusID:254733288">254733288</a>.</cite></li></ul>

</div></div><div><div class="zim-footer">

This article is issued from <a class="external text" title="Last edited on 2025-08-05" href="https://en.wikipedia.org/wiki/?title=Feature_engineering&oldid=1304311455">Wikipedia</a>. The text is available under <a class="external text" href="https://creativecommons.org/licenses/by-sa/4.0/deed.en">Creative Commons Attribution-Share Alike 4.0</a> unless otherwise noted. Additional terms may apply for the media files.

</div>

</div></div>

</div>

</main>

</div>

</body></html>