CMPE 257 final project
Project Description: Online shoppers have access to millions of products from large retailers, which can be overwhelming and lead to empty shopping carts. Recommender systems help guide shoppers towards products that match their interests and motivations, improving the shopping experience. Machine Learning can enhance recommender systems, predicting which products a customer is likely to view, add to their cart, or purchase in real-time. No single model exists that can simultaneously optimize multiple objectives in recommender systems. The OTTO group is the largest German online shop, with more than 10 million products from over 19,000 brands, and your work could help retailers select more relevant items to recommend to their customers. In this Project, we will design a Machine Learning model to predict the click-through rate , add-to-cart rate , and the conversion rates based on previous session events from the OTTO dataset.
Approach: Major Steps involved in the Project are : Data Extraction, Transformation and Loading Data Pre Processing EDA of the Entire Dataset System Design and Formulation of the Recommendation Engine Training and Testing the models Performance Observations & Hypertuning Comparisons of different algorithms and approaches Model Inference Pipeline
Dataset: https://www.kaggle.com/competitions/otto-recommender-system/data