What this Algorithm is Used For
Use this algorithm to recommend items (products, services, etc) based on their similarity to other items. This is an easy way to improve the effectiveness of an online commerce presence by automating discovery of relevant items for customers.
Common Use Cases
Ecommerce - Recommending new products or services for e-commerce
Online Gaming - Recommending virtual goods for online gaming
Finance - Recommend new financial products and services
Item based recommenders make recommendations based on similarity of items. They use a defined statistical method (Log Likelihood, Pearson Correlation, etc) to determine the similarity of items based on a set of characteristics or "features". Unlike user based recommenders, item based recommenders need at least one pre-defined item preference for a new user. This is used as the basis for recommending other, similar items.
Note: Item based recommendations return faster results than user based recommendations for large data sets or real-time recommendations. The main reason for this is item similarities are relatively constant compared to user profiles which are constantly changing. As a result, item similarities can be stored in a database for quick recall to provide recommendations whereas user profiles must be created per user.
Data Input and Output
Data Formats Accepted:
Columns Required in Data File:
1. Sample data set with Table of users with at least two characteristics defined per user. This data is used to train the algorithm
2. New data set with user profiles
Collaborative Filtering, Recommendations, Machine Learning