classification

Project Proposal Template

Question/need:

• Instacart, a grocery ordering and delivery app, makes it easy for users to keep their pantries and refrigerators filled without ever leaving their homes. Users select products through the Instacart app, and personal shoppers handle the in-store shopping and delivery.

  The data science team at Instacart uses transactional data to develop models to recommend items to users and enhance the online shopping experience. In this project, we will try to segment Instacart's customer base so that each class of customers can receive relevant recommendations.

Data Description:

• I am looking at Instacart's first public dataset release, “The Instacart Online Grocery Shopping Dataset 2017”. This anonymized dataset contains a sample of over 3 million grocery orders from more than 200,000 Instacart users. For each user, between 4 and 100 of their orders are provided, with the sequence of products purchased in each order. Week and hour of the day information is also provided, and a relative measure of time between orders. The data dictionary can be accessed here.

Tools:

• I am using SQL to query in data, pandas for data analysis and manipiulation, matplotlib and seaborn for visualizations, and scikit-learn for classification and machine learning.

MVP Goal:

• We will produce visualizations that show interesting insights from initial data exploration, and suggest some possible customer classes.