Upload your data and get a complete ibm hr employee attrition drivers report. Free.
or click to browse · max 3 MB
Running ibm hr employee attrition drivers analysis...
Sent to — interactive charts, statistical results, R code, and AI insights.
Analyze another fileDual-model approach combining logistic regression (interpretable odds ratios with 95% CI) and XGBoost with gain-based feature importance as a SHAP proxy, applied to 20 employee attributes spanning compensation, workload, satisfaction, tenure, and demographics
Use this when you have HR employee records with a binary attrition outcome and want to identify and rank the factors driving voluntary turnover using both interpretable statistics and non-linear machine learning
Do not use if your dataset lacks a clear binary attrition column, has fewer than 100 employee records, or if you need causal inference rather than predictive association
Built for: HR Business Partners, People Analytics Managers, Compensation & Benefits Specialists, Talent Acquisition Directors, Chief Human Resources Officers
Typical data source: Employee HR dataset with attrition outcome (Yes/No), demographics (age, department, job role), compensation fields (monthly income, job level, stock options), satisfaction ratings (job, environment, work-life balance), and tenure fields (years at company, years in current role, years since last promotion)
Dataset with 20 columns
Minimum 100 rows
Binary classification: Attrition (Yes/No, converted to 1/0). The IBM HR dataset has 1,470 employees × 35 attributes. Baseline attrition rate ~16.1%; top driver in published Kaggle notebooks is OverTime, followed by MonthlyIncome, JobRole, YearsAtCompany, and BusinessTravel. Analysis compares a logistic regression (directional, interpretable) against xgboost with SHAP values (non-linear, ranked importance).
Attrition rates broken down by department, overtime status, business travel frequency, and job level to identify highest-risk segments
Job role attrition rates ranked to identify which titles face disproportionate voluntary turnover
Logistic regression odds ratios (forest plot) showing which predictors significantly increase or decrease attrition odds after controlling for all other factors
Complete logistic regression coefficient table with p-values and 95% confidence intervals for every predictor
XGBoost gain-based feature importance ranked by mean absolute contribution to attrition prediction
Overtime-by-department cross-tab of attrition rates showing whether overtime-driven attrition is uniform or concentrated in specific departments
Kaplan-Meier retention probability over tenure years highlighting at which milestones attrition risk peaks
ROC curve showing logistic regression discrimination quality between attritors and stayers
Plain-English interpretation — what the numbers mean, what's significant, and what to do next.
Need something simpler? Tf038 Live Ttest — When you only need to test whether a single metric like monthly income or job satisfaction differs significantly between employees who left vs. stayed
Need more power? Anova Factorial — When you need to analyze interaction effects between multiple categorical HR factors such as department and overtime and job level on attrition rates
Similar: Churn Drivers
Identify employees at highest risk of quitting
Identify employees at highest risk of quitting
See our FAQ for details on pricing, data privacy, and how the analysis works. Every report includes a Methodology section showing the statistical test, assumptions checked, and diagnostics run.
Run any analysis on your own data — validated R analyses, interactive reports, AI insights, and PDF export.
Try Free — No Credit Card