Kaggle's "Allstate Purchase Prediction Challenge."
Project paper, code, and presentation slides: https://github.com/justmarkham/kaggle-allstate
Goal : Predict which car insurance options a customer will buy.
Problem:
(1) There are 7 car insurance options, each with 2 to 4 possible values.
(2) Values are identified by number (0,1,2, etc)
(3) “quote” consists of a single combination of those 7 options.
(4) Customers review one or more qutotes before making their purchase.
dataset:
quotes history and purchase history.
diffculty:
there are 2304 possible combinations of options.
no partial credit. no feedback given on which options were wrong.
naive approach:
for each customer, just predict that they will purchase the last set of options they were qutoed.
Accuracy vs random guessing.
- Recommendation System: Collaborative filtering,Content Based Filtering,Hybrid Recommendation Filtering
- Customer Lifetime Value Modelling:
Defining objectives for the company- growth, expenditures, future sales, net profit etc.
Optimise business marketing strategies.
Adjusting campaign and advertisement.
Decide cross sell and up sell according to customer’s purchase.
CLV helps to decide customer acquisition cost, the cost of attracting customers.customer data, car data(age,value) - Customer Retention- Churn Model
- Fraud Detection
- Important Reviews- Improved Customer Service
Ecommerce analytics quick guide
https://www.smartinsights.com/ecommerce/ecommerce-analytics/
E-commerce conversion funnel
https://www.smartinsights.com/ecommerce/ecommerce-analytics/ecommerce-conversion-rates/
Conversion rates for US vs Europe vs Asia Pacific for the travel industry
Lead generation and landing page conversion rates by sector