ATMOSPHERE was presented at the "ACM/SIGAPP Symposium on Applied Computing", from 8th till 12th April 2019, in Limassol (Cyprus). For the past thirty-four years, the ACM Symposium on Applied Computing (SAC) has been a primary gathering forum for applied computer scientists, computer engineers, software engineers, and application developers from around the world. SAC 2019 is sponsored by the ACM Special Interest Group on Applied Computing (SIGAPP).
ATMOSPHERE was invited to presente a paper focused on local surrogate models
The increase in sophistication and complexity of recommendation algorithms has turned them into black boxes where the algorithmic reasoning behind the predictions is hard to understand by users. A popular approach for increasing model interpretability in the machine learning community is the Locally Interpretable Model-agnostic Explanations (LIME), which proposes to learn local interpretable models for explaining single predictions of any model. In this paper, we propose an adaptation of LIME for any recommender system. ATMOSPHERE experts evaluated their adaptation of LIME on Factorization Machines, a well-known black-box recommender algorithm trained on MovieLens 20M dataset. They compared their approach to a state-of-the-art model-agnostic method based on association rules and show that their proposed adaptation is a promising alternative since it is comparable in terms of fidelity, i.e., can locally mimic the behavior of a complex recommender, and has the additional advantage of enabling different styles of explanations. Finally, a case study for investigating the feasibility and limitations of their proposed adaptation was presented.