DeepFair: Deep Learning for Improving Fairness in Recommender Systems
This addresses fairness issues in recommender systems for minority users, representing an incremental improvement in balancing equity and precision.
The paper tackled the problem of unfair recommendations for minority groups in recommender systems by proposing a deep learning-based collaborative filtering algorithm that balances fairness and accuracy without requiring demographic data, achieving fair recommendations without significant accuracy loss.
The lack of bias management in Recommender Systems leads to minority groups receiving unfair recommendations. Moreover, the trade-off between equity and precision makes it difficult to obtain recommendations that meet both criteria. Here we propose a Deep Learning based Collaborative Filtering algorithm that provides recommendations with an optimum balance between fairness and accuracy without knowing demographic information about the users. Experimental results show that it is possible to make fair recommendations without losing a significant proportion of accuracy.