Recommendation systems need not always involve complex machine-learning techniques. With enough data on hand, one can develop recommendation systems with little effort. One of the simplest recommendation systems is a look-up table based on user-indicated profile settings. When you have data on many users and their behavior, collaborative filtering is an easy solution for implementing recommendations. For example, in an e-commerce solution you could use collaborative filtering to determine which users that purchased a sleeping bag have also purchased a flashlight, lantern and bug repellent. Content-based recommendation systems go a step further and incorporate greater sophistication in predicting what a user is likely to want, based on that user’s interactions.
This article demonstrates how to develop simple recommendation systems in Redis based on user-indicated interests and collaborative filtering. It’s a quick guide to:
1. Redis data structures and commands for recommendations
2. Generating recommendations based on user interests
3. Collaborative filtering based on user-item associations and their ratings
4. Advanced recommendations using Machine Learning via Redis-ML module