During a 30-day simulation, Starbucks sends out 10 different offers to its 17,000 customers. The transactions made by customers and offer related activities are recorded. The goal of this project is twofold:
- to analyze the customer's attitude towards a received promotional offer;
- to build a classifier to predict whether a customer likes an offer based on attributes of customer and offer.
The project is developed under Python 3.7 with the following packages:
- pandas
- NumPy
- seaborn
- scikit-learn
- LightGBM
- XGBoost
- tabulate
- tqdm
Starbucks and Udacity are greatly acknowledged for prividing the data used in this project.