AI-Powered Employee Performance Analysis for INX Future Inc.
This project focuses on analyzing employee performance at INX Future Inc. with the aim of identifying key factors that influence performance and providing actionable recommendations to reduce employee attrition. The project involves the following key tasks:
- Data preprocessing and exploratory data analysis.
- Feature selection and engineering.
- Model training and evaluation.
- Insights generation and recommendations.
To run this project locally, follow these steps:
-
Clone the repository:
git clone https://github.com/yourusername/employee-performance-analysis.git cd employee-performance-analysis
-
Create and activate a virtual environment:
python -m venv venv source venv/bin/activate # On Windows, use `venv\Scripts\activate`
-
Install the required libraries:
pip install -r requirements.txt
-
Launch Jupyter Notebook:
jupyter notebook
The dataset contains employee data, including features such as age, gender, department, job role, satisfaction levels, and performance ratings. Below are the key features used in this analysis:
EmpNumber
,Age
,Gender
,EducationBackground
,MaritalStatus
,EmpDepartment
,EmpJobRole
BusinessTravelFrequency
,DistanceFromHome
,EmpEducationLevel
,EmpEnvironmentSatisfaction
EmpHourlyRate
,EmpJobInvolvement
,EmpJobLevel
,EmpJobSatisfaction
NumCompaniesWorked
,OverTime
,EmpLastSalaryHikePercent
,EmpRelationshipSatisfaction
TotalWorkExperienceInYears
,TrainingTimesLastYear
,EmpWorkLifeBalance
,ExperienceYearsAtThisCompany
ExperienceYearsInCurrentRole
,YearsSinceLastPromotion
,YearsWithCurrManager
,Attrition
,PerformanceRating
The dataset is processed and used for predictive modeling to determine the factors affecting employee performance and attrition.
employee-performance-analysis/
│
├── data/ # Dataset files
├── notebooks/ # Jupyter notebooks for analysis
├── models/ # Trained models
├── reports/ # Generated analysis reports
├── src/ # Source code for data processing and modeling
│ ├── data_processing.py
│ ├── feature_engineering.py
│ └── model_training.py
├── README.md # Project README file
├── requirements.txt # Python libraries required
└── .gitignore # Git ignore file
-
Data Preprocessing:
- Run
data_processing.py
to clean and preprocess the data.
- Run
-
Feature Engineering:
- Run
feature_engineering.py
to perform feature selection and engineering.
- Run
-
Model Training:
- Run
model_training.py
to train models and evaluate their performance.
- Run
-
Analysis:
- Use the Jupyter notebooks in the
notebooks/
directory to explore data, perform analysis, and generate insights.
- Use the Jupyter notebooks in the
- High positive correlation between
Age
andTotalWorkExperienceInYears
indicates that more experienced employees tend to be older. - Negative correlation between
Attrition
andTotalWorkExperienceInYears
suggests that employees with more experience are less likely to leave the company.
- Gradient Boosting Classifier (GBClassifier) achieved an
AUC
score of 0.96, indicating outstanding discriminative ability. - Random Forest and XGBoost models also demonstrated high accuracy and stability.
- Focus on improving job satisfaction and work-life balance to reduce attrition.
- Offer tailored retention strategies for high-risk groups based on education and experience.
- Minimize frequent business travel to reduce stress and turnover.
Contributions are welcome! Please fork the repository and create a pull request with your changes.
This project is licensed under the MIT License. See the LICENSE
file for more details.
For any questions or inquiries, please contact:
-
Muhammad Azam Khan: [email protected] --github :[https://github.com/Muhammad-Azam-khan]
-
LinkedIn: [https://www.linkedin.com/in/me/]