A Performance Prediction Approach to Enhance Collaborative Filtering Performance

Abstract

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: Abstract. Performance prediction has gained increasing attention in the IR field since the half of the past decade and has become an established research topic in the field. The present work restates the problem in the area of Collaborative Filtering (CF), where it has barely been researched so far. We investigate the adaptation of clarity-based query performance predictors to predict neighbor performance in CF. A predictor is proposed and introduced in a kNN CF algorithm to produce a dynamic variant where neighbor ratings are weighted based on their predicted performance. The properties of the predictor are empirically studied by, first, checking the correlation of the predictor output with a proposed measure of neighbor performance. Then, the performance of the dynamic kNN variant is examined on different sparsity and neighborhood size conditions, where the variant consistently outperforms the baseline algorithm, with increasing difference on small neighborhoods.

Predicting the Performance of Recommender Systems: An Information Theoretic Approach

“…The first problem was already researched in [3], where a dynamic collaborative filtering algorithm outperformed the standard formulation by promoting neighbors that are expected to perform better in a nearest-neighbor recommendation algorithm. We are currently working on the second problem, namely, how to dynamically choose the best weights in a recommender ensemble.…”

Predicting performance in recommender systems

“…This adaptation, however, is not straightforward, since RS rank and recommend items without an explicit user query, using other inputs instead. We explore different formulations of the user clarity under different models in [6] and [8]. Different assumptions for the random variables derive different models, all of them grounded on previous probability formulations in RS such as [15].…”

An Adaptive Framework for Enhancing Recommendation Using Hybrid Techniques

“…Furthermore, they claimed that the conventional weighted sum prediction formula used in item-based CF is not correct for very sparse datasets. Thus, they provided another prediction formula and empirically evaluated it.Bellogín and Castells in [11], investigated the adaptation of clarity-based query performance predictors to predict neighbour performance in CF. They explored the use of performance prediction techniques to enhance the selection and weighting of neighbours in CF.…”