1-844-696-6465 (US)        +91 77600 44484        help@dezyre.com

All state Insurance Purchase Prediction Challenge - Python

For each customer in the test set, you must predict the seven coverage options they end up purchasing.

Users who bought this project also bought

What will you learn

  • Data management using python
  • Exploratory data analysis
  • Predicting which insurance option the customer will choose
  • application of machine learning methods
  • finding best ML method for prediction

What will you get

  • Access to recording of the complete project
  • Access to all material related to project like data files, solution files etc.


  • This project assumes that you have a good knowledge of Data Science and the Python language. If not - we recommend you to take the Data Science in Python course first.

Project Description

The training and test sets contain transaction history for customers that ended up purchasing a policy. For each customer_ID, you are given their quote history. In the training set you have the entire quote history, the last row of which contains the coverage options they purchased. In the test set, you have only a partial history of the quotes and do not have the purchased coverage options. These are truncated to certain lengths to simulate making predictions with less history (higher uncertainty) or more history (lower uncertainty).

For each customer_ID in the test set, you must predict the seven coverage options they end up purchasing.

Each customer has many shopping points, where a shopping point is defined by a customer with certain characteristics viewing a product and its associated cost at a particular time.

  • Some customer characteristics may change over time (e.g. as the customer changes or provides new information), and the cost depends on both the product and the customer characteristics.
  • A customer may represent a collection of people, as policies can cover more than one person.
  • A customer may purchase a product that was not viewed!