Dimitre Kostadinov

Analysis of strategies for building group profiles

Today most of existing personalization systems (e.g content recommenders, or targeted ad) focus on individual users and ignore the social situation in which the services are consumed However, many human activities are social and involve several individuals whose tastes and expectations must be taken into account by the service providers When a group profile is not available, different profile aggregation strategies can be applied to recommend adequate content and services to a group of users based on their individual profiles In this paper, we consider an approach intended to determine the factors that influence the choice of an aggregation strategy We present a preliminary evaluation made on a real large-scale dataset of TV viewings, showing how group interests can be predicted by combining individual user profiles through an appropriate strategy The conducted experiments compare the group profiles obtained by aggregating individual user profiles according to various strategies to the “reference” group profile obtained by directly analyzing group consumptions.

Evaluation of group profiling strategies

Most of the existing personalization systems such as content recommenders or targeted ads focus on individual users and ignore the social situation in which the services are consumed. However, many human activities are social and involve several individuals whose tastes and expectations must be taken into account by the system. When a group profile is not available, different profile aggregation strategies can be applied to recommend adequate items to a group of users based on their individual profiles. We consider an approach intended to determine the factors that influence the choice of an aggregation strategy. We present evaluations made on a large-scale dataset of TV viewings, where real group interests are compared to the predictions obtained by combining individual user profiles according to different strategies.

A personalized access model: concepts and services for content delivery platforms

Access to relevant information, adapted to users needs, preferences and environment, is a challenge in many applications running in content delivery platforms, like IPTV, VoD and mobile Video. In order to provide users with personalized content, applications use various techniques such as content recommendation, content filtering, preference-driven queries, etc. These techniques exploit different knowledge organized into profiles and contexts. However, there is not a common understanding of these concepts and there is no clear foundation of what a personalized access model should be. This paper contributes to this concern by providing, through a meta model, a clear distinction between profile and context, and by providing a set of services which constitutes a basement to the definition of a personalized access model (PAM). Our PAM definition allows applications to interoperate in multiple personalization scenarios, including, preference-based recommendation, context-aware content delivery, personalized access to multiple contents, etc. Concepts and services proposed are tightly defined with respect to real applications requirements provided by Alcatel-Lucent.

On the Use of LSH for Privacy Preserving Personalization

The Locality Sensitive Hashing (LSH) technique of scalably finding nearest-neighbors can be adapted to enable discovering similar users while preserving their privacy. The key idea is to compute the user profile on the end-user device, apply LSH on the local profile, and use the LSH cluster identifier as the interest group identifier of a user. By properties of LSH, the interest group comprises other users with similar interests. The collective behavior of the members of the interest group is anonymously collected at some aggregation node to generate recommendations for the group members. The quality of recommendation depends on the efficiency of the LSH clustering algorithm, i.e. its capability of gathering similar users. In contrast, with conventional usage of LSH (for scalability and not privacy), in our framework one can not perform a linear search over the cluster members to identify the nearest neighbors and to prune away false positives. A good clustering quality is therefore of functional importance for our system. We report in this work how changing the nature of LSH inputs, which in our case corresponds to the user profile representations, impacts the performance of LSH-based clustering and the final quality of recommendations. We present extensive performance evaluations of the LSH-based privacypreserving recommender system using two large datasets of MovieLens ratings and Delicious bookmarks, respectively.

Stimulus-based sandbox for learning resource dependencies in virtualized distributed applications

In this paper, we present an approach for automated profiling of cloud-based distributed applications. The failure dependencies within or between application nodes can be methodically elucidated by dynamically applying a series of unitary perturbations on the underlying computing resources. Each such perturbation in a node acts as a stimulus which propagates to performance meters of dependent nodes and reveals correlations and causal relations between the respective entities. We have developed an instrumented framework for methodical elucidation of these dependencies which covers an extensive set of failure situations. The prime application of our approach is the behavior learning of a distributed application under various resource insufficiency conditions for Quality of Service management and Root Cause Analysis.