Frito-Lay Attrition Model Prediction

This project delves into the intricate relationship between employee attrition and salary dynamics, using data science to uncover the underlying patterns that drive workforce stability. By analyzing records from 870 employees, we explore how factors like job satisfaction, income, and career progression influence retention rates across different departments. Through machine learning models, including K-Nearest Neighbors (KNN) and Naïve Bayes, we predict attrition while addressing challenges like class imbalance and feature interactions. A robust regression analysis further reveals that while salary and experience strongly correlate with income, financial incentives alone do not guarantee retention—job satisfaction and career trajectory play equally complex roles. Key findings show that younger employees earning under $5,000 per month exhibit the highest turnover, and advanced job levels see only a marginal reduction in attrition. These insights offer actionable strategies for HR professionals and business leaders, emphasizing the need for a balanced approach that aligns financial growth with job fulfillment. By blending statistical rigor with real-world relevance, this study provides a data-driven lens into the evolving workplace, equipping organizations with the knowledge to build a more engaged and resilient workforce.

This section presents an overview of the dataset, which includes records for 870 employees with a mix of categorical and numerical variables. A heatmap of feature correlations highlights key relationships between employee attributes, setting the foun

This section presents an overview of the dataset, which includes records for 870 employees with a mix of categorical and numerical variables. A heatmap of feature correlations highlights key relationships between employee attributes, setting the foundation for further analysis.

Exploratory Data Analysis (EDA) identifies key factors contributing to employee attrition. Insights reveal a strong relationship between job satisfaction, monthly income, and attrition, with younger employees earning less than $5,000 being the most l

Exploratory Data Analysis (EDA) identifies key factors contributing to employee attrition. Insights reveal a strong relationship between job satisfaction, monthly income, and attrition, with younger employees earning less than $5,000 being the most likely to leave.

This section outlines different machine learning models applied to predict attrition, including K-Nearest Neighbors (KNN), linear regression, and interaction models. Model performance highlights challenges such as imbalanced data and weak predictive

This section outlines different machine learning models applied to predict attrition, including K-Nearest Neighbors (KNN), linear regression, and interaction models. Model performance highlights challenges such as imbalanced data and weak predictive power in linear regression.

A Naïve Bayes classifier is implemented with feature engineering to improve predictions. The model achieves 77.36% accuracy, with significant predictive power derived from income bands, job satisfaction, and interaction terms.

A Naïve Bayes classifier is implemented with feature engineering to improve predictions. The model achieves 77.36% accuracy, with significant predictive power derived from income bands, job satisfaction, and interaction terms.

A regression model is built to predict monthly income using features such as age, department, years at the company, job level, and total working years. The model achieves a strong fit with an R-squared value of approximately 91.12%, showing a clear r

A regression model is built to predict monthly income using features such as age, department, years at the company, job level, and total working years. The model achieves a strong fit with an R-squared value of approximately 91.12%, showing a clear relationship between experience and salary.

This section integrates attrition and salary predictions, exploring departmental differences in attrition rates and salary levels. A strong interplay between age, income, and attrition patterns is observed across departments.

This section integrates attrition and salary predictions, exploring departmental differences in attrition rates and salary levels. A strong interplay between age, income, and attrition patterns is observed across departments.

Insights into job satisfaction, salary discrepancies, and attrition patterns by department are presented. Findings reveal that higher job satisfaction does not always correlate with lower attrition, and employees with 1-5 years at the company show th

Insights into job satisfaction, salary discrepancies, and attrition patterns by department are presented. Findings reveal that higher job satisfaction does not always correlate with lower attrition, and employees with 1-5 years at the company show the highest turnover rates.