Counterfactual Contextual Multi-Armed Bandit to Diagnose Post-Harvest Diseases of Apple

Post-harvest diseases of apple are one of the major issues in the economical sector of apple production, causing severe economical losses to producers. Thus, we developed DSSApple, a picture-based decision support system able to help users in the diagnosis of apple diseases. Specifically, this paper addresses the problem of sequentially optimizing for the best diagnosis, exploiting past interactions with the system and their contextual information (i.e., the evidence provided by the users), while exploring the set of candidate diseases. This online learning problem is commonly addressed in the literature through a stochastic active learning paradigm - i.e., Contextual Multi-Armed Bandit (CMAB). The methodology interactively updates the decision model considering the success of each past interaction with respect to the context provided in each round. However, contextual information is very often partial and inadequate to handle such a complex decision making problem. On the other hand, human-made decisions implicitly include unobserved factors (referred to as unobserved confounders) that significantly influence their choices. In this paper, we take advantage of the information embedded in the observed human decisions to marginalize confounders and improve the capability of the CMAB model to identify the correct diagnosis. Specifically, we propose a Counterfactual Thompson Sampling (CF-TS), a CMAB model based on the causal concept of counterfactual. The proposed model is validated with offline experiments based on data collected through a large user study on DSSApple application. The results prove that CF-TS is able to significantly outperform both traditional CMAB algorithms and observed user decisions, in the real-world task of predicting the correct apple disease.