Gaming Engagement Predictor

A Python project that trains a multinomial logistic regression model to predict player engagement levels (Low, Medium, High) using the Predict Online Gaming Behavior Dataset.

Installation

1. Clone the repository

   git clone https://github.com/username/gaming-engagement-predictor.git
   cd gaming-engagement-predictor

2. Create and activate a virtual environment

   python3 -m venv venv
   source venv/bin/activate    # On Windows: venv\Scripts\activate

3. Install dependencies

   pip install -r requirements.txt

Usage

Run the main script to preprocess data, train the model, and generate output:

python panda.py

• Outputs:

  • Console logs of data loading, model training, and evaluation metrics.
  • all_players_with_high_probability.csv: each player’s probability of being in the High engagement bucket.

Data

• Source: El Kharoua, R. (n.d.). Predict Online Gaming Behavior Dataset [Data set]. Kaggle. Retrieved June 8, 2025.
• File: Predict_Online_Gaming_Behavior.csv

Dependencies

• Python 3.13
• pandas
• numpy
• scikit-learn

See requirements.txt for exact versions.

Citation

If you use this work, please cite:

El Kharoua, R. (n.d.). Predict Online Gaming Behavior Dataset [Data set]. Kaggle. Retrieved June 8, 2025.

Harris et al. (2020) for NumPy & McKinney (2010) for pandas & Pedregosa et al. (2011) for scikit-learn.

License

This project is licensed under the MIT License. See LICENSE for details.