This course will guide you through building and evaluating recommender systems using Python. You鈥檒l start with the basics of recommender systems and Python programming, progressing through techniques like content-based filtering, collaborative filtering, and matrix factorization. By the end of the course, you'll have the skills to create real-world recommender systems and evaluate their performance. The course starts with an introduction to Python and recommender systems, covering types of recommenders, implicit vs. explicit ratings, and top-N architecture. You'll learn to evaluate systems using metrics like RMSE, MAE, hit rates, and diversity, and understand concepts like churn and novelty. As the course progresses, you'll explore content-based filtering and K-Nearest-Neighbors (KNN). Then, you鈥檒l dive into collaborative filtering methods, including user-based and item-based techniques. You鈥檒l also gain hands-on experience implementing these methods using Python and datasets like MovieLens. This course is perfect for learners with basic Python knowledge who want to dive into machine learning applications in recommendation systems. It鈥檚 ideal for those interested in creating, evaluating, and deploying recommender systems.
Exercise Solution: Hybrid Recommenders
Loading...
Skills You'll Learn
Matrix Factorization, Collaborative Filtering, Recommender Systems, Data preprocessing and feature engineering, System Evaluation and Optimization, Deep Learning for Recommendations, Content-based Filtering, Python Programming, Recommender System Design
From the lesson
Hybrid Approaches
In this module, we will explore hybrid recommendation approaches, combining multiple algorithms to improve recommendation accuracy and diversity. Practical exercises will guide you through implementing and evaluating hybrid systems.
Taught By
Packt - Course Instructors