This GitHub project focuses on analyzing the last purchase behavior of customers who engaged in OmniChannel shopping, which refers to customers who made purchases both online and offline. The dataset used in this project comprises historical shopping data, providing valuable insights into the purchasing patterns of customers within the time frame of 2020-2021.
Key Features:
OmniChannel Customer Segmentation: Utilize advanced data analysis techniques to segment customers based on their shopping behavior, distinguishing between online and offline purchases. Customer Lifetime Value (CLTV) Prediction: Leverage models such as BG-NBD (Beta Geometric Negative Binomial Distribution) and Gamma-Gamma to predict the customer lifetime value, offering estimates on the expected revenue generated by each customer over their entire relationship with the business. Behavioral Analysis: Perform in-depth analysis of customer behavior, including purchase frequency, churn probability, average transaction value, and other key metrics, providing insights into customer preferences and trends. Marketing Strategy Optimization: Utilize the insights gained from the analysis to optimize marketing strategies, enabling targeted campaigns, personalized offers, and improved customer retention efforts. Business Profitability Enhancement: Empower businesses to make data-driven decisions to maximize overall profitability by optimizing resource allocation, inventory management, and pricing strategies based on the identified customer segments and their buying patterns. By exploring and implementing these analyses and techniques, this project aims to help businesses in the retail domain, particularly the FLO Store Chain, leverage OmniChannel customer data to gain actionable insights for informed decision-making and to enhance customer experiences, ultimately driving growth and success in a highly competitive market.