Using cognitive models to understand and counteract the effect of self-induced bias on recommendation algorithms

Recommendation algorithms trained on a training set containing sub-optimal decisions may increase the likelihood of making more bad decisions in the future. We call this harmful effect self-induced bias, to emphasize that the bias is driven directly by the user’s past choices. In order to better understand the nature of self-induced bias of recommendation algorithms that are used by older adults with cognitive limitations, we have used agent-based simulation. Based on state-of-the-art results in psychology of aging and cognitive science, as well as our own empirical results, we have developed a cognitive model of an e-commerce client that incorporates cognitive decision-making abilities. We have evaluated the magnitude of self-induced bias by comparing results achieved by simulated agents with and without cognitive limitations due to age. We have also proposed new recommendation algorithms designed to counteract self-induced bias. The algorithms take into account user preferences and cognitive abilities relevant to decision making. To evaluate the algorithms, we have introduced 3 benchmarks: a simple product filtering method and two types of widely used recommendation algorithms: Content-Based and Collaborative filtering. Results indicate that the new algorithms outperform benchmarks both in terms of increasing the utility of simulated agents (both old and young), and in reducing self-induced bias.