This repo is based on the first project of a business case elaborated for the Machine Learning course at Hult International Business School by the professor Chase Kusterer.
The business case is based on Apprentice Chef, Inc. - a fictitious meal kit delivery company.
This project involved developing a predictive model and predict how much revenue to expect over the first year of each customer's life cycle.
Yi_Yuan_A1_Analysis.ipynb : Jupyter Notebook with the analysis. This analysis has a heavy focus in feature engineering. Engineered features were essential for the final model, as well as for the the data-driven insights. I focused on developing a simple, explainable model in order to have more interpretability.
Yi Yuan A1_Write_Up.pdf : Contains the data-driven insights based on the business problem.
Apprentice_Chef_Dataset.xlsx : Contains the data provided by the data science team.
Apprentice_Chef_Data_Dictionary.xlsx : Metadata of each feature found in the dataset.
Apprentice Chef, Inc. is an innovative company with a unique spin on cooking at home. Developed for the busy professional that has little to no skills in the kitchen, they offer a wide selection of daily-prepared gourmet meals delivered directly to your door. Each meal set takes at most 30 minutes to finish cooking at home and also comes with Apprentice Chef's award-winning disposable cookware (i.e. pots, pans, baking trays, and utensils), allowing for fast and easy cleanup. Ordering meals is very easy given their user-friendly online platform and mobile app.
After 3 years serving customers across the San Francisco Bay Area, the executives at Apprentice Chef have come to realize that over 90% of their revenue comes from customers that have been ordering meal sets for 12 months or less. Given this information, they would like to better understand how much revenue to expect from each customer within their first year of orders.