Paolo Cremonesi

Cross-Domain Recommender Systems

Most recommender systems work on single domains, i.e., they recommend items related to the same domain where users have expressed ratings. However, the integration of different domains into one recommender system could allow users to span over different types of items. For instance, users that have watched live TV programs could like to be recommended with on-demand movies, music, mobile applications, friends to connect to, etc. This paper focuses on cross-domain collaborative recommender systems, whose aim is to suggest items related to multiple domains. We first formalize the cross-domain problem in order to provide a common framework for the classification and the evaluation of state-of-the-art algorithms. We later define a new class of cross-domain algorithms based on neighborhood collaborative filtering, either item-based or user-based. The main idea is to first model the classical similarity relationships (e.g., Pearson, cosine) as a direct graph and to later explore all possible paths connecting users or items in order to find new, cross-domain, relationships. The algorithms have been tested on three cross-domain scenarios artificially reproduced by partitioning the Netflix dataset.

Investigating the Persuasion Potential of Recommender Systems from a Quality Perspective: An Empirical Study

Recommender Systems (RSs) help users search large amounts of digital contents and services by allowing them to identify the items that are likely to be more attractive or useful. RSs play an important persuasion role, as they can potentially augment the users’ trust towards in an application and orient their decisions or actions towards specific directions. This article explores the persuasiveness of RSs, presenting two vast empirical studies that address a number of research questions. First, we investigate if a design property of RSs, defined by the statistically measured quality of algorithms, is a reliable predictor of their potential for persuasion. This factor is measured in terms of perceived quality, defined by the overall satisfaction, as well as by how users judge the accuracy and novelty of recommendations. For our purposes, we designed an empirical study involving 210 subjects and implemented seven full-sized versions of a commercial RS, each one using the same interface and dataset (a subset of Netflix), but each with a different recommender algorithm. In each experimental configuration we computed the statistical quality (recall and F-measures) and collected data regarding the quality perceived by 30 users. The results show us that algorithmic attributes are less crucial than we might expect in determining the user’s perception of an RS’s quality, and suggest that the user’s judgment and attitude towards a recommender are likely to be more affected by factors related to the user experience. Second, we explore the persuasiveness of RSs in the context of large interactive TV services. We report a study aimed at assessing whether measurable persuasion effects (e.g., changes of shopping behavior) can be achieved through the introduction of a recommender. Our data, collected for more than one year, allow us to conclude that, (1) the adoption of an RS can affect both the lift factor and the conversion rate, determining an increased volume of sales and influencing the user’s decision to actually buy one of the recommended products, (2) the introduction of an RS tends to diversify purchases and orient users towards less obvious choices (the long tail), and (3) the perceived novelty of recommendations is likely to be more influential than their perceived accuracy. Overall, the results of these studies improve our understanding of the persuasion phenomena induced by RSs, and have implications that can be of interest to academic scholars, designers, and adopters of this class of systems.

Analysis of cold-start recommendations in IPTV systems

In this paper we evaluate the performance of different collaborative algorithms in cold-start situations, where the initial lack of ratings may affect the quality of the algorithms. The evaluation has been performed on the pay-per-view datasets collected by two IP-television providers over a period of several months. The analysis shows that item-based algorithms perform better with respect to SVD-based ones in the early stage of the cold-start problem. Moreover, the accuracy of SVD-based algorithms, when using few latent factors, decreases with the time-evolution of the dataset. On the contrary, the same algorithms used with a large-enough number of latent features increase their accuracy with time and may outperform the item-based algorithms.

A QoS-based selection approach of autonomic grid services

The Web service composition (WSC) is the process of building an instance of an abstract workflow by combining appropriate Web services that satisfies given QoS requirements. In general, QoS requirements consists of a number of constraints. The selection process requires global optimization and can be formalized as a mixed integer linear programming problem which cannot be solved in polynomial time. However, since the number of submitted workflows is large and the QoS is highly dynamic, the fast selection of composite Web Services is particularly important. In this paper, we present a QoS broker-based framework for Web services execution in autonomic grid environments. The main goal of the framework is to support the broker in selecting Web services based on the required QoS. To achieve this goal, we propose a novel approach: since successive composed Web services requests can have the same task to Web service assignment, we address the Multiple Instance WSC (MI-WSC) problem optimizing simultaneously the set of requests which will be submitted to the system in the successive time interval instead of independently computing a solution for each incoming request. Experimental results show that the proposed algorithm has better performance with respect to existing techniques. Moreover, the qualities of the selected composite Web services are not significantly different from the optimal ones.

An Evaluation Methodology for Collaborative Recommender Systems

Recommender systems use statistical and knowledge discovery techniques in order to recommend products to users and to mitigate the problem of information overload. The evaluation of the quality of recommender systems has become an important issue for choosing the best learning algorithms. In this paper we propose an evaluation methodology for collaborative filtering (CF) algorithms. This methodology carries out a clear, guided and repeatable evaluation of a CF algorithm. We apply the methodology on two datasets, with different characteristics, using two CF algorithms: singular value decomposition and naive bayesian networks.

Robust Workload Estimation in Queueing Network Performance Models

Traditional approaches for capacity planning are based on queueing network models. However, modeling with queueing networks requires the knowledge of the service demands of each class of workloads at each device described in the model. In real systems, such service demands can be very difficult to measure. In this paper, we present an optimization-based technique to address the problem. The technique is formulated as a robust linear parameter estimation that can be used with both closed and open queueing network models. We consider the case where aggregate measurements (throughput and utilization) are available. Such measurements are typically much easier to obtain than the service demands. We present experimental results which prove the effectiveness of the constrained and robust linear estimation.

Content-Based Video Recommendation System Based on Stylistic Visual Features

This paper investigates the use of automatically extracted visual features of videos in the context of recommender systems and brings some novel contributions in the domain of video recommendations. We propose a new content-based recommender system that encompasses a technique to automatically analyze video contents and to extract a set of representative stylistic features (lighting, color, and motion) grounded on existing approaches of Applied Media Theory. The evaluation of the proposed recommendations, assessed w.r.t. relevance metrics (e.g., recall) and compared with existing content-based recommender systems that exploit explicit features such as movie genre, shows that our technique leads to more accurate recommendations. Our proposed technique achieves better results not only when visual features are extracted from full-length videos, but also when the feature extraction technique operates on movie trailers, pinpointing that our approach is effective also when full-length videos are not available or when there are performance requirements. Our recommender can be used in combination with more traditional content-based recommendation techniques that exploit explicit content features associated to video files, to improve the accuracy of recommendations. Our recommender can also be used alone, to address the problem originated from video files that have no meta-data, a typical situation of popular movie-sharing websites (e.g., YouTube) where every day hundred millions of hours of videos are uploaded by users and may contain no associated information. As they lack explicit content, these items cannot be considered for recommendation purposes by conventional content-based techniques even when they could be relevant for the user.

Analysis and implementation of a parallelization strategy on a Navier-Stokes solver for shear flow simulations

Abstract A parallel computational solver for the unsteady incompressible three-dimensional Navier–Stokes equations implemented for the numerical simulation of shear flow cases is presented. The computational algorithms include Fourier expansions in the streamwise and spanwise directions, second-order centered finite differences in the direction orthogonal to the solid walls, third-order Runge–Kutta procedure in time in which both convective and diffusive terms are treated explicitly; the fractional step method is used for time marching. Based on the numerical algorithms implemented within the computational solver, three different (MPI based) parallelization strategies are devised. The three schemes are evaluated with particular attention to the impact of the communications onto the whole computational procedure, and one of them is implemented. Computations are executed on two different parallel machines and results are shown in terms of parallel performance. Processes using different number of processors combined with different number of computational grid points are tested.

Do Metrics Make Recommender Algorithms

Recommender systems are used to suggest customized products to users. Most recommender algorithms create collaborative models by taking advantage of web user profiles. In the last years, in the area of recommender systems, the Netflix contest has been very attractive for the researchers. However, many recent papers on recommender systems present results evaluated with the methodology used in the Netflix contest in domains where the objectives are different from the contest (e.g., top-N recommendation task). In this paper we do not propose new recommender algorithms but, rather, we compare different aspects of the official Netflix contest methodology based on RMSE and holdout with methodologies based on k-fold and classification accuracy metrics.We show, with case studies, that different evaluation methodologies lead to totally contrasting conclusions about the quality of recommendations.

Performance evaluation of parallel systems

In this paper performance evaluation methodologies that have been applied to the analysis of parallel systems are reviewed together with the specific performance metrics. We concentrate on a few selected performance studies of parallel system components, i.e., processor, memory, interconnection network, input/output, and operating system. We demonstrate the utility of the performance evaluation methodologies for identification of system bottlenecks, performance forecasting, and future system design.