Academic Journals Database
Disseminating quality controlled scientific knowledge

Hybrid Collaborative Filtering Based o n Probabilistic Prototype

Author(s): Murali Mohan . Thomurthy | Harada Koichi | Balakrishna . Annepu

Journal: International Journal of Engineering Trends and Technology
ISSN 2231-5381

Volume: 5;
Issue: 5;
Start page: 272;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Memory based | Model - based | K - NN | Item - based | Similarity | Prototype.

Collaborative filtering recommender systems-recommend items by identifying other users with similar taste and use their opinions for recommendation.In this paper the concepts of Content-Boosted Collaborative Filtering algorithm is discussed and proposed for modification in the existing approach using probabilistic measures to improve the performance. The methodology using Probabilistic Prototypeused for predictions have been discussed. The Formulas that were used to implement these models including Bayes conditional probability, rating, Significance Weighting Factor, Harmonic Mean Weighting and Self-Weighting and Prediction. The measured Mean Absolute Error (MAE) of the proposed model is compared with available models from literature and finally the performance analysis is done based on parameter MAE.

Tango Jona
Tangokurs Rapperswil-Jona

     Save time & money - Smart Internet Solutions