Narrow Results

Collaborative Filtering (CF) has become the most popular approach for developing Recommender Systems in diverse business applications. Unfortunately, problems such as the cold-start problem (i.e., new users or items enter the system and for those no previous preference information is available) and the gray sheep problem (i.e., cases in which a user profile does not match any other profile in the user community) are widely recognized for hindering recommendation effectiveness of traditional CF methods. To alleviate such problems, substantial research has focused on enhancing CF with social information about users (e.g., social relationships and communities). However, despite the crescent interest in social-based approaches, researches and practitioners face the challenge of developing their own Recommender System architecture for appropriately combining social and collaborative filtering methods to improve recommendation results. In this paper, we address this issue by introducing a flexible architecture to support researchers and practitioners in the task of designing real-world Recommender Systems that exploit social network data. We focus on detailing our proposed architecture modules and their interplay, potential algorithms for extracting and combining relevant social information, and candidate technologies for handling diverse and massive data volumes. Additionally, we provide an empirical analysis demonstrating the effectiveness of the proposed architecture on alleviating the cold-start problem over a concrete experimental case.

Recommender systems help users find relevant items efficiently based on their interests and historical interactions with other users. They are beneficial to businesses by promoting the sale of products and to user by reducing the search burden. Recommender systems can be developed by employing different approaches, including collaborative filtering (CF), demographic filtering (DF), content-based filtering (CBF) and knowledge-based filtering (KBF). However, large amounts of data can produce recommendations that are limited in accuracy because of diversity and sparsity issues. In this paper, we propose a novel hybrid method that combines user–user CF with the attributes of DF to indicate the nearest users, and compare four classifiers against each other. This method has been developed through an investigation of ways to reduce the errors in rating predictions based on users’ past interactions, which leads to improved prediction accuracy in all four classification algorithms. We applied a feature combination method that improves the prediction accuracy and to test our approach, we ran an offline evaluation using the 1M MovieLens dataset, well-known evaluation metrics and comparisons between methods with the results validating our proposed method.

An escape room is a physical puzzle solving game, where participants solve a series of riddles within a limited time to exit a locked room. Escape rooms differ in their theme, environment, and difficulty, and people hence often differ on their preferences over escape rooms. As such, recommendation systems can help people in deciding which room to visit. In this paper, we describe the properties of the escape rooms recommendation problem, with respect to other popular recommendation problems. We describe a dataset of reviews collected within a current system. We provide an empirical comparison between a set of recommendation algorithms over two problems, top-N recommendation and rating prediction. In both cases, a KNN method performed the best.

Advances in medical science simultaneously benefit patients while contributing to an over-whelming complexity of medicine with a decision space of thousands of possible diagnoses, tests, and treatment options. Medical expertise becomes the most important scarce health-care resource, reflected in tens of millions in the US alone with deficient access to specialty care. Combining the growing wealth of electronic medical record data with modern recommender algorithms has the potential to synthesize the clinical community’s expertise into an executable format to manage this information overload and improve access to personalized care suggestions. We focus here specifically on outpatient consultations for (Endocrine) specialty expertise, one of the highest demand and most amenable areas for electronic consultation systems. Specifically we develop and evaluate models to predict the clinical orders of these initial specialty referral consultations using an ensemble of feed-forward neural networks as compared to multiple baseline algorithms. As benchmarks closer to the existing standard of care, we used diagnosis-based clinical checklists based on our review of literature and practice guidelines (e.g., Up-to-Date) for each common referral diagnosis as well as existing electronic consult referral guides. Results indicate that such automated algorithms trained on historical data can provide more personalized decision support with greater accuracy than existing benchmarks, with the potential to power fully digital consultation services that could consolidate utilization of scarce medical expertise, improving consistency of quality and access to care for more patients.