This data science project focuses on predicting customer churn in a retail store using data provided by CSSA IUST as part of the Data Science Crash Course. The dataset includes information for 1500+ customers, including the day and the corresponding purchase amount. The primary goal is to identify customers who are more likely to leave the store and provide insights through exploratory data analysis (EDA).
-
Data: The dataset includes 1500+ files which are each for a unique customer and are placed in
Data
folder. -
Code: The code directory includes Python scripts for performing exploratory data analysis, customer churn prediction, and visualization.
- Visualized customer spending patterns over time.
- Explored behaviour of customers.
- Investigated the distribution of purchase amounts and identified outliers.
- Analyzed store-related features, such as special events.
- Investigated the impact of store events on customer transactions.
- Developed a machine learning model to predict customer churn using clustering method.
- Utilized features derived from the EDA process.
- Evaluated the model's performance using appropriate metrics.
This project provides valuable insights into customer behavior within the retail store. The exploratory data analysis sheds light on patterns and trends, while the churn prediction model offers a proactive approach to identify customers at risk of leaving. By understanding these dynamics, the store can take targeted actions to retain customers and improve overall customer satisfaction.
- Python 3
- Jupyter Notebooks
- Required Python libraries (requirements.txt)
Feel free to explore the provided code and datasets to gain deeper insights into the project. If you have any questions or suggestions, please reach out via email or create an issue in the repository.
Note: This project was completed as part of the CSSA IUST Data Science Crash Course.