1.1 - 8.10 - Recommender Functions (ML Engine) - Teradata Vantage

Teradata Vantage™ - Machine Learning Engine Analytic Function Reference

Teradata Vantage
Release Number
October 2019
Content Type
Programming Reference
Publication ID
English (United States)

A recommender system is an information filtering system that predicts the ratings or preferences that users assign to entities like books, songs, movies, and other products.

The goal of a recommender system is to recommend to users items or products that might interest them. The typical recommendation task is to predict the rating a user would give to an item. ML Engine recommender functions are based on Collaborative Filtering (CF), which relies only on historical rankings of products by users to identify similarities between users and between products, and thus to identify products that are new to a particular user that the user would rate highly.

Function Description
WSRecommender (ML Engine) Item-based, collaborative filtering function that uses weighted-sum algorithm to make recommendations. Predicts rating user would give to item by calculating average of ratings user has given similar items, weighted by similarity score between items.

For information about weighted-sum algorithms, see "Item-Based Collaborative Filtering recommendation Algorithms." Badrul Sarwar, George Karypis, Joseph Konstan and John Riedl.

KNNRecommender (ML Engine) and KNNRecommenderPredict (ML Engine) Used together. Similar to WSRecommender, but attempt to increase prediction accuracy by adjusting for systematic biases and replacing heuristic calculations of similarity coefficients with global optimization that simultaneously estimates all weights.

For more information, see "Improved Neighborhood-based Collaborative Filtering." Robert M. Bell and Yehuda Koren.