Qualitative Analysis of User-Based and Item-Based Prediction Algorithms for Recommendation Agents

Abstract

Recommendation agents employ prediction algorithms to provide users with items that match their interests. In this paper, several prediction algorithms are described and evaluated, some of which are novel in that they combine user-based and item-based similarity measures derived from either explicit or implicit ratings. Both statistical and decision-support accuracy metrics of the algorithms are compared against different levels of data sparsity and different operational thresholds. The first metric evaluates the accuracy in terms of average absolute deviation, while the second evaluates how effectively predictions help users to select highquality items. The experimental results indicate better performance of item-based predictions derived from explicit ratings in relation to both metrics. Category-boosted predictions lead to slightly better predictions when combined with explicit ratings, while implicit ratings, in the context that have been defined in this paper, perform much worse than explicit ratings. r $ This paper is part of the special issue of selected best papers of the 9th international workshop on cooperative information agents (CIA

SINVLIO: Using semantics and fuzzy logic to provide individual investment portfolio recommendations

“…As stated before, there are not works appliying this metric in the field of application of SINVLIO. However we can see that SINVLIO results is in the line of [67], where results peek 0.65, provides better results than [27], [37], where coverage are around 0.38 and are less than [59]. In this latter case, where coverage slightly less than perfect for typical level of sparsity (Coverage: 99%), the dataset is more convenient to produce good results.…”

A Survey Paper on E-Learning Recommender System

“…Random prediction has a great probability of failure. Thus, it has never been taken seriously by any researcher or vendor and only serves as reference point1, helping to compare the quality of the results obtained by the utilization of a more sophisticated algorithm [15].…”

Family Aware TV Program and Settings Recommender

“…Other recommender systems analyze the content to provide recommendations. The context aware recommender utilizes context data as an additional input to the recommendation task, alongside information of users and items [13,14,15,16,17,18,19,20,21,22,23,24].…”