Deviation-Based Learning: Training Recommender Systems Using Informed User ChoiceJunpei Komiyama, Shunya Noda
This paper proposes a new approach to training recommender systems called deviation-based learning. The recommender and rational users have different knowledge. The recommender learns user knowledge by observing what action users take upon receiving recommendations. Learning eventually stalls if the recommender always suggests a choice: Before the recommender completes learning, users start following the recommendations blindly, and their choices do not reflect their knowledge. The learning rate and social welfare improve substantially if the recommender abstains from recommending a particular choice when she predicts that multiple alternatives will produce a similar payoff.
On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit ApproachJunpei Komiyama, Shunya Noda
We analyze statistical discrimination in hiring markets using a multi-armed bandit model. Myopic firms face workers arriving with heterogeneous observable characteristics. The association between the worker's skill and characteristics is unknown ex ante; thus, firms need to learn it. Laissez-faire causes perpetual underestimation: minority workers are rarely hired, and therefore, the underestimation tends to persist. Even a marginal imbalance in the population ratio frequently results in perpetual underestimation. We propose two policy solutions: a novel subsidy rule (the hybrid mechanism) and the Rooney Rule. Our results indicate that temporary affirmative actions effectively alleviate discrimination stemming from insufficient data.