A Recommender System based on Idiotypic Artificial Immune Networks

TL;DR

This paper introduces an Artificial Immune System inspired by biological immune characteristics for film recommendation, emphasizing diversity and matching rather than optimization, and compares its performance to other collaborative filtering methods.

Contribution

It presents a novel AIS approach utilizing antigen-antibody and idiotypic interactions for improved diversity in collaborative filtering recommendations.

Findings

The AIS effectively identifies a subset of good matches for recommendations.

It demonstrates comparable or improved performance relative to traditional CF techniques.

The system emphasizes diversity over single optimal solutions.

Abstract

The immune system is a complex biological system with a highly distributed, adaptive and self-organising nature. This paper presents an Artificial Immune System (AIS) that exploits some of these characteristics and is applied to the task of film recommendation by Collaborative Filtering (CF). Natural evolution and in particular the immune system have not been designed for classical optimisation. However, for this problem, we are not interested in finding a single optimum. Rather we intend to identify a sub-set of good matches on which recommendations can be based. It is our hypothesis that an AIS built on two central aspects of the biological immune system will be an ideal candidate to achieve this: Antigen-antibody interaction for matching and idiotypic antibody-antibody interaction for diversity. Computational results are presented in support of this conjecture and compared to those found by other CF techniques.