[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290349-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290349-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","employee-attrition-leveraging-machine-learning-explainability-to-identify-key-predictors-of-turnover","Employee Attrition - Leveraging Machine Learning Explainability to Identify Key Predictors of Turnover","","Employee Attrition analyzes how high turnover costs and disrupted team dynamics can be mitigated using interpretable machine learning. It reviews limitations of traditional predictive models for attrition and applies ML explainability methods to reveal key drivers behind turnover predictions. The study uses the IBM Employee Attrition dataset, trains a Random Forest with an 80/20 split, and evaluates accuracy and classification performance. Explainability results highlight Monthly Income, Age, and overtime as major predictors, while PDP, LIME, and ICE support actionable retention insights.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/employee-attrition-leveraging-machine-learning-explainability-to-identify-key-predictors-of-turnover/290349/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/employee-attrition-leveraging-machine-learning-explainability-to-identify-key-predictors-of-turnover/290349.png","ImageObject",300,407,{"name":42,"@type":43},"Eliana","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-01","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why are traditional machine learning models limited for employee attrition analysis?","Question",{"text":63,"@type":64},"Traditional models can predict attrition accurately but often do not explain transparently which factors drive each prediction, limiting actionable HR decision-making.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What dataset and modeling approach are used in the study?",{"text":68,"@type":64},"The study uses the public IBM Employee Attrition dataset with a binary target (Attrition: Yes/No) and trains a Random Forest with an 80% training and 20% test split.",{"name":70,"@type":61,"acceptedAnswer":71},"Which factors are identified as the most influential predictors of turnover?",{"text":72,"@type":64},"Feature importance results indicate Monthly Income and Age are the most influential, and overtime status is associated with higher likelihood of leaving.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290349,1789641441,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":22,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":80,"read_time":30,"preview_page_count":4},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","Employee Attrition: Leveraging Machine Learning Explainability  \nto Identify Key Predictors of Turnover  \nDinh Cuong (Ernest) Nguyen, Gregory Lovisolo Faculty Advisor: Dan Tenney, Ph.D.  \nSchool of Engineering University of Bridgeport, Bridgeport, CT  \nIntroduction  \nProblem Statement  \n• High turnover rates incur significant financial costs, and employee attrition can disrupt team dynamics, lower morale, and negatively impact overall organizational performance.  \n• Traditional Machine Learning (ML) models such as decision trees, and random forests can accurately predict employee attrition, they often fail to provide transparency into the factors driving these predictions.  \n• Machine Learning Explainability (MLX) addresses the limitations of traditional machine learning and augments traditional HR decisionmaking by providing transparency into how machine learning models make their predictions.  \nResearch Questions  \n• What are the most significant factors contributing to employee attrition?  \n• How does MLX improve HR decision-making?  \n• How do individual features interact to influence employee attrition?  \n• Can counterfactual explanations provide actionable insights for retention strategies?  \nRelated works  \n• Fallucchi et.al (2020) used Gaussian Naïve Bayes classifier to explore the dataset. It reveals the best recall rate (0 .54), since it measures the ability of a classifier to find all the positive instances and achieves an overall false negative rate equal to 4.5% of the total observations.  \n• In 2023 , Ogunbowale explain neural networks and random forest for employee retention, but the research have not explored the hidden factors behind the machine learning models.  \n• There are many other studies that also compare how good each machine learning model is if the hyperparameters change to improve model performance. (Chowdhury [et. al](et. al). , 2023, Jain et. al. , 2020 , Alduayj & Rajpoot, 2018) .  \n• At the International Conference on Decision Aid Sciences and Applications (DASA) in 2022 , Sekaran & Shanmugam introduced an explainable artificial intelligence solution for practical application of employee turnover. The idea mentioned used Local Interpretable Model-Agnostic Explainer (LIME) and Shapley Additive eXplainer (SHAP) on interpreting the factors deciding employee attrition. The conference research has not provided how the individual features interact to influence employee attrition and whether counterfactual explanations provide actionable insights for retention strategies.  \nMethodology  \n• IBM Employee Attrition dataset is a publicly available, comprehensive, real-world dataset from a global technology company, offering a holistic view of the working environment.  \n• The target variable in this dataset is Attrition, which is a binary variable with the values 'Yes'(indicating the employee left) and 'No' (indicating the employee stayed) .  \n• This dataset was prepared for machine learning models (Random Forests), was split into two parts training (80%) and test (20%) .  \n• MLX techniques: Feature Importance, Partial Dependence Plots (PDP), LIME (Local Interpretable Model-agnostic Explanations), ICE (Individual Conditional Expectation)  \n| \u003Cbr>Results and Discussion\u003Cbr>Model Performance |  |  |  |\n| --- | --- | --- | --- |\n| • The Random Forest algorithm achieved an accuracy of 87.76%, which indicates a strong ability to classify employees who are likely to stay or leave.\u003Cbr>• The classification report showed that while the model performed well in predicting employees who would stay (precision = 0.88 , recall = 0.99 , f1-score = 0.93), its performance for predicting employees likely to leave was less robust (precision = 0.67 , recall = 0.15 , f1-score = 0.25) . |  |  | |\n| Feature Importance |  |  |  |\n| |  | • The most influential factors contributing to employee attrition are Monthly Income and Age with the highest importance score of 0.072 and 0.05.\u003Cbr>• Overtime status shows that employees who work ove","cbCaiaA61F65tzLN","https://ap.wps.com/l/cbCaiaA61F65tzLN","pdf",1074354,"English","# Introduction\n## Problem Statement\n## Research Questions\n## Related Works\n# Methodology\n## Dataset and Target Variable\n## MLX Techniques\n# Results and Discussion\n## Model Performance\n## Feature Importance\n## ROC Curve\n## Partial Dependence Plots (PDP)\n## LIME (Local Interpretable Model-agnostic Explanations)\n## ICE (Individual Conditional Expectation)","[{\"question\":\"Why are traditional machine learning models limited for employee attrition analysis?\",\"answer\":\"Traditional models can predict attrition accurately but often do not explain transparently which factors drive each prediction, limiting actionable HR decision-making.\"},{\"question\":\"What dataset and modeling approach are used in the study?\",\"answer\":\"The study uses the public IBM Employee Attrition dataset with a binary target (Attrition: Yes/No) and trains a Random Forest with an 80% training and 20% test split.\"},{\"question\":\"Which factors are identified as the most influential predictors of turnover?\",\"answer\":\"Feature importance results indicate Monthly Income and Age are the most influential, and overtime status is associated with higher likelihood of leaving.\"}]","Employee Attrition - Leveraging Machine Learning Explainability to Identify Key Predictors of Turnover | PDF"]