We experiment on two real e-commerce datasets and survey more than 30 popular e-commerce platforms to reveal what methods work best for product recommendations in industrial settings. Despite recent academic advances in the field, we observe that simple methods such as best-seller lists dominate deployed recommendation engines in e-commerce. We find our empirical findings to be well-aligned with those of the survey, where in both cases simple personalized recommenders achieve higher ranking than more advanced techniques. We also compare the traditional random evaluation protocol to our proposed chronological sampling method, which can be used for determining the optimal time-span of the training history for optimizing the performance of algorithms. This performance is also affected by a proper hyperparameter tuning, for which we propose golden section search as a fast alternative to other optimization techniques.

The goal of our study is to provide a holistic view on various ethical challenges that complicate the design and use of recommender systems (RS). Our findings materialize into an ethical recommendation framework, which maps RS development stages to the corresponding ethical concerns, and further down to known solutions and the proposed user-adjustable controls. The need for such a framework is dictated by the apparent lack of research in this particular direction and the severity of consequences stemming from the neglect of the code of ethics in recommendations. The framework aims to aid RS practitioners in staying ethically alert while taking morally charged design decisions. At the same time, it would give users the desired control over the sensitive moral aspects of recommendations via the proposed “ethical toolbox”. The idea is embraced by the participants of our feasibility study.

This work presents an extension of Thompson Sampling bandit policy for orchestrating the collection of base recommendation algorithms for e-commerce. We focus on the problem of item-to-item recommendations, for which multiple behavioral and attribute-based predictors are provided to an ensemble learner. In addition, we detail the construction of a personalized predictor based on k-Nearest Neighbors (kNN), with temporal decay capabilities and event weighting. We show how to adapt Thompson Sampling to realistic situations when neither action availability nor reward stationarity is guaranteed. Furthermore, we investigate the effects of priming the sampler with pre-set parameters of reward probability distributions by utilizing the product catalog and/or event history, when such information is available. We report our experimental results based on the analysis of three real-world e-commerce datasets.

Despite the increasing interest towards session-based and streaming recommender systems, there is still a lack of publicly available evaluation frameworks supporting both these paradigms. To address the gap, we propose FlowRec — an extension of the streaming framework Scikit-Multiflow, which opens plentiful possibilities for prototyping recommender systems operating on sessionized data streams, thanks to the underlying collection of incremental learners and support for real-time performance tracking. We describe the extended functionalities of the adapted prequential evaluation protocol, and develop a competitive recommendation algorithm on top of Scikit-Multiflow’s implementation of a Hoeffding Tree. We compare our algorithm to other known baselines for the next-item prediction task across three different domains.

Reported evidence of biased matchmaking calls into question the ethicality of recommendations generated by a machine learning algorithm. In the context of dating services, the failure of an automated matchmaker to respect the user’s expressed sensitive preferences (racial, religious, etc.) may lead to biased decisions perceived by users as unfair. To address the issue, we introduce the notion of preferential fairness, and propose two algorithmic approaches for re-ranking the recommendations under preferential fairness constraints. Our experimental results demonstrate that the state of fairness can be reached with minimal accuracy compromises for both binary and non-binary attributes.