This project aims to predict customer churn using machine learning algorithms. The goal is to identify customers who are likely to stop using a service or product, allowing businesses to take proactive measures to retain them. The project includes the following key components:
- Data Preprocessing: The project starts by loading and preprocessing a dataset containing customer information and behavior. This involves handling missing values, encoding categorical variables, and scaling numerical features.
- Model Evaluation: The project evaluates the performance of different machine learning algorithms, including Decision Trees, Random Forests, Support Vector Machines, and more. The models are trained and tested using a variety of metrics, including accuracy, precision, recall, and F1-score.
- Model Selection: The project selects the best-performing model based on the evaluation metrics and uses it to make predictions on new, unseen data.
- Python 3.11 or higher
- Required libraries:
pandas,numpy,scikit-learn,matplotlib,seaborn,PyYAML
- Clone the repository:
git clone https://github.com/your-username/Churn-Prediction.git - Install required libraries:
pip install -r requirements.txt
- Run the main script:
python main.py - Use command-line arguments to customize the project:
-cor--classifier: specify the classifier to use (default:AdaBoost)-tor--test-size: specify the test size for train-test split (default:0.2)-por--preprocessing-method: specify the preprocessing method to use (default:standardization)
python main.py: run the project with default settingspython main.py -c KNN -t 0.5 -p robust-scaling: run the project with KNN classifier, 50% test size, and robust scaling preprocessing
main.py: main entry point for the projectconfig.py: configuration file for the projectdataset.py: data loading and preprocessing moduleclassification.py: classification moduleplot_confusion_matrix.py: confusion matrix plotting modulerequirements.txt: required libraries for the project