Udacity Data Scientist Project IV: Udacity_Project_Capstone_Project_Starbucks

This repository contains all related files of the Udacity data scientist nanoprogram Capstone Project: Starbucks

Installation

The code should run in the Python 3.6.* environment pandas=1.1.3 matplotlib=2.1.0 seaborn= 0.9.0 scikit-learn=0.23.2

Data source

data

Project Motivation

The project aims to build a model for finding the best offer to the target demographic groups. Try to figure out the questions below:

1. Which groups of customer respond best to the offers
2. Predict if customers will use the offers
3. Predict what offer types these customers would like

File Description

The data directory contains all the metadata files, including portfolio.json, profile.json and transcript.json. The Starbucks_Capstone_notebook is a draft now and showcases all the work related with the final models.

Results

The main findings are published on medium.com:Starbucks: Attracting Customers with Offers

Licensing, Authors, Acknowledgements

Must give credit to Starbucks for the data.