Abstract
Many online communities and services continuously generate data that can be used by recommender systems. When explicit ratings are not available, rating prediction algorithms are not directly applicable. Instead, data consists of positive-only user-item interactions, and the task is therefore not to predict ratings, but rather to predict good items to recommend - item prediction. One particular challenge of positive-only data is how to interpret absent user-item interactions. These can either be seen as negative or as unknown preferences. In this paper, we propose a recency-based scheme to perform negative preference imputation in an incremental matrix factorization algorithm designed for streaming data. Our results show that this approach substantially improves the accuracy of the baseline method, outperforming both classic and state-of-the-art algorithms.

Abstract

Abstract
Numerous stream mining algorithms are equipped with forgetting mechanisms, such as sliding windows or fading factors, to make them adaptive to changes. In recommender systems those techniques have not been investigated thoroughly despite the very volatile nature of users' preferences that they deal with. We developed five new forgetting techniques for incremental matrix factorization in recommender systems. We show on eight datasets that our techniques improve the predictive power of recommender systems. Experiments with both explicit rating feedback and positive-only feedback confirm our findings showing that forgetting information is beneficial despite the extreme data sparsity that recommender systems struggle with. Improvement through forgetting also proves that users' preferences are subject to concept drift.

Abstract

Abstract
This paper is about long-term travel time prediction in public transportation. However, it can be useful for a wider area of applications. It follows a heterogeneous ensemble approach with dynamic selection. A vast set of experiments with a pool of 128 tuples of algorithms and parameter sets (a&ps) has been conducted for each of the six studied routes. Three different algorithms, namely, random forest, projection pursuit regression and support vector machines, were used. Then, ensembles of different sizes were obtained after a pruning step. The best approach to combine the outputs is also addressed. Finally, the best ensemble approach for each of the six routes is compared with the best individual a&ps. The results confirm that heterogeneous ensembles are adequate for long-term travel time prediction. Namely, they achieve both higher accuracy and robustness along time than state-of-the-art learners.

Abstract
The main goal of recommender systems is to assist users in finding items of their interest in very large collections. The use of good automatic recommendation promotes customer loyalty and user satisfaction because it helps users to attain their goals. Current methods focus on the immediate value of recommendations and are evaluated as such. This is insufficient for long term goals, either defined by users or by platform managers. This is of interest in recommending learning resources to learn a target concept, and also when a company is organizing a campaign to lead users to buy certain products or moving to a different customer segment. Therefore, we believe that it would be useful to develop recommendation algorithms that promote the goals of users and platform managers (e.g. e-shop manager, e-learning tutor, ministry of culture promotor). Accordingly, we must define appropriate evaluation methodologies and demonstrate the concept on practical cases.