The project aims to analyze customer churn in a utility company using machine learning techniques. Leveraging historical customer data, including consumption patterns, contract details, and demographic information, the project seeks to identify factors contributing to churn and develop predictive models to forecast customer churn. By understanding the drivers of churn and predicting future churn events, the company can proactively implement targeted retention strategies to mitigate customer attrition and improve customer satisfaction. Through this data-driven approach, the project aims to optimize customer retention efforts and enhance the long-term sustainability and profitability of the utility company.
- ml_case_training_data : The data of customer detailed infos on consumption, forecast usage, dates, net margin, sales channels etc
- ml_case_training_hist_data : The data of historical prices on different period
- ml_case_training_output : The data of churn prediction
- Code : The entire project on data processing, analytics, model training, performance metrics etc
- requirements.txt/ Contains the packages needs to run the project
- README.md: Provides project overview, setup instructions, and usage guidelines.
- Jupyter Notebook (.ipynb)
- Python 3.10.12
- Numpy 1.25.2
- Pandas 1.5.3
- Matplotlib 3.7.1
- Seaborn 0.13.1
- Scipy 1.11.4
- Scikit-learn
- Open the files in Google Colab or Anaconda Jupyter Notebook
- Install the requirements.txt
- Import the dataset to the notebook
- You're good to go!
$ pip install -r requirements.txt
This project is licensed under the MIT License. See the LICENSE file for more details.