Most existing cross-domain recommendation algorithms focus on modeling ratings, while ignoring review texts. The review text, however, contains rich information, which can be utilized to alleviate data sparsity limitations, and interpret transfer patterns. In this paper, we investigate how to utilize the review text to improve cross-domain collaborative filtering models. The challenge lies in the existence of non-linear properties in some transfer patterns. Given this, we extend previous transfer learning models in collaborative filtering, from linear mapping functions to non-linear ones, and propose a cross-domain recommendation framework with the review text incorporated. Experimental verifications have demonstrated, for new users with sparse feedback, utilizing the review text obtains 10% improvement in the AUC metric, and the nonlinear method outperforms the linear ones by 4%.

Items in real-world recommender systems exhibit certain hierarchical structures. Similarly, user preferences also present hierarchical structures. Recent studies show that incorporating the explicit hierarchical structures of items or user preferences can improve the performance of recommender systems. However, explicit hierarchical structures are usually unavailable, especially those of user preferences. Thus, there's a gap between the importance of hierarchical structures and their availability. In this paper, we investigate the problem of exploring the implicit hierarchical structures for recommender systems when they are not explicitly available. We propose a novel recommendation framework HSR to bridge the gap, which enables us to capture the implicit hierarchical structures of users and items simultaneously. Experimental results on two real world datasets demonstrate the effectiveness of the proposed framework.

We generally use hit rate to measure the performance of item recommendation algorithms. In addition to hit rate, we consider another two important factors which are ignored by most previous works. First, whether users are satisfied with the recommended items. It is possible that a user has bought an item but dislikes it. Hence high hit rate does not reflect high customer satisfaction. Second, whether the website retailers are satisfied with the recommendation results. If a customer is interested in two products and wants to buy one of them, it may be better to suggest the item which can help bring more profit. Therefore, a good recommendation algorithm should not only consider improving hit rate but also consider optimizing user satisfaction and website revenue. In this paper, we propose two algorithms for the above purposes and design two modified hit rate based metrics to measure them. Experimental results on 10 real-world datasets show that our methods can not only achieve better hit rate, but improve user satisfaction and website revenue comparing with the state-of-the-art models.

In this paper, we propose a framework for using reinforcement learning (RL) algorithms to learn good policies for personalized ad recommendation (PAR) systems. The RL algorithms take into account the long-term effect of an action, and thus, could be more suitable than myopic techniques like supervised learning and contextual bandit, for modern PAR systems in which the number of returning visitors is rapidly growing. However, while myopic techniques have been well-studied in PAR systems, the RL approach is still in its infancy, mainly due to two fundamental challenges: how to compute a good RL strategy and how to evaluate a solution using historical data to ensure its “safety” before deployment. In this paper, we propose to use a family of off-policy evaluation techniques with statistical guarantees to tackle both these challenges. We apply these methods to a real PAR problem, both for evaluating the final performance and for optimizing the parameters of the RL algorithm. Our results show that a RL algorithm equipped with these off-policy evaluation techniques outperforms the myopic approaches. Our results also give fundamental insights on the difference between the click through rate (CTR) and life-time value (LTV) metrics for evaluating the performance of a PAR algorithm.

Tour recommendation and itinerary planning are challenging tasks for tourists, due to their need to select Points of Interest (POI) to visit in unfamiliar cities, and to select POIs that align with their interest preferences and trip constraints. We propose an algorithm called PersTour for recommending personalized tours using POI popularity and user interest preferences, which are automatically derived from real-life travel sequences based on geo-tagged photos. Our tour recommendation problem is modelled using a formulation of the Orienteering problem, and considers user trip constraints such as time limits and the need to start and end at specific POIs. In our work, we also reflect levels of user interest based on visit durations, and demonstrate how POI visit duration can be personalized using this time-based user interest. Using a Flickr dataset of four cities, our experiments show the effectiveness of PersTour against various baselines, in terms of tour popularity, interest, recall, precision and F1-score. In particular, our results show the merits of using time-based user interest and personalized POI visit durations, compared to the current practice of using frequency-based user interest and average visit durations.

Matrix factorization (MF) is a prevailing collaborative filtering method for building recommender systems. It requires users to upload their personal preferences to the recommender for performing MF, which raises serious privacy concerns. This paper proposes a differentially private MF mechanism that can prevent an untrusted recommender from learning any users' ratings or profiles. Our design decouples computations upon users' private data from the recommender to users, and makes the recommender aggregate local results in a privacy-preserving way. It uses the objective perturbation to make sure that the final item profiles satisfy differential privacy and solves the challenge to decompose the noise component for objective perturbation into small pieces that can be determined locally and independently by users. We also propose a third-party based mechanism to reduce noises added in each iteration and adapt our online algorithm to the dynamic setting that allows users to leave and join. The experiments show that our proposal is efficient and introduces acceptable side effects on the precision of results.

Recommender systems (RSs) provide an effective way of alleviating the information overload problem by selecting personalized choices. Online social networks and user-generated content provide diverse sources for recommendation beyond ratings, which present opportunities as well as challenges for traditional RSs. Although social matrix factorization (Social MF) can integrate ratings with social relations and topic matrix factorization can integrate ratings with item reviews, both of them ignore some useful information. In this paper, we investigate the effective data fusion by combining the two approaches, in two steps. First, we extend Social MF to exploit the graph structure of neighbors. Second, we propose a novel framework MR3 to jointly model these three types of information effectively for rating prediction by aligning latent factors and hidden topics. We achieve more accurate rating prediction on two real-life datasets. Furthermore, we measure the contribution of each data source to the proposed framework.

Good music recommenders should not only suggest quality recommendations, but should also allow users to discover new/niche music. User studies capture explicit feedback on recommendation quality and novelty, but can be expensive, and may have difficulty replicating realistic scenarios. Lack of effective offline evaluation methods restricts progress in music recommendation research. The challenge is finding suitable measures to score recommendation quality, and in particular avoiding popularity bias, whereby the quality is not recognised when the track is not well known. This paper presents a low cost method that leverages available social media data and shows it to be effective. Not only is it based on explicit feedback from many users, but it also overcomes the popularity bias that disadvantages new/niche music. Experiments show that its findings are consistent with those from an online study with real users. In comparisons with other offline measures, the social media score is shown to be a more reliable proxy for opinions of real users. Its impact on music recommendation is its ability to recognise recommenders that enable discovery, as well as suggest quality recommendations.

The need for diversification manifests in various recommendation use cases. In this work, we propose a novel approach to diversifying a list of recommended items, which maximizes the utility of the items subject to the increase in their diversity. From a technical perspective, the problem can be viewed as maximization of a modular function on the polytope of a submodular function, which can be solved optimally by a greedy method. We evaluate our approach in an offline analysis, which incorporates a number of baselines and metrics, and in two online user studies. In all the experiments, our method outperforms the baseline methods.

We propose a model, Lexicographic Partially Observable Markov Decision Process (LPOMDP), which extends POMDPs with lexicographic preferences over multiple value functions. It allows for slack--slightly less-than-optimal values--for higher-priority preferences to facilitate improvement in lower-priority value functions. Many real life situations are naturally captured by LPOMDPs with slack. We consider a semi-autonomous driving scenario in which time spent on the road is minimized, while maximizing time spent driving autonomously. We propose two solutions to LPOMDPs--Lexicographic Value Iteration (LVI) and Lexicographic Point-Based Value Iteration (LPBVI), establishing convergence results and correctness within strong slack bounds. We test the algorithms using real-world road data provided by Open Street Map (OSM) within 10 major cities. Finally, we present GPU-based optimizations for point-based solvers, demonstrating that their application enables us to quickly solve vastly larger LPOMDPs and other variations of POMDPs.