Models Andmethods for Forecasting Recommendations for Collaborative Recommender Systems
Journal Title: Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì - Year 2018, Vol 901, Issue
Abstract
This article analyzes the current state of models and methods for constructing recommender systems. The main classes of tasks that solve recommender systems are highlighted. The features of the application of the method of collaborative (joint) filtering are shown. A mixed numerical-categorical clustering method for searching for user groups that uses numerical rating and demographic characteristics of users has been developed, a hybrid method for searching for user groups has been developed that uses the coefficient of usersubject matrix sparseness.
Authors and Affiliations
Mykhaylo Lobur, Yuriy Stekh
Keywords
Related Articles
- EP ID EP575323
- DOI -
- Views 141
- Downloads 0
Heterogeneous data processing in web-systems information resources
In the paper the method of integrated processing of heterogeneous information resources web-systems is described. This method is based on the model of data description as a coherent combination of data values, rules of d...
Monitoring System of Technological Processes of “Smart Enterprise”
It is determined that the main tasks for the monitoring of technological processes at an enterprise are the collection, storage, visualization, preliminary analytical and intellectual processing of technological data in...
Hurst exponent evaluated via calculated by box-counting method on short time series example fractal dimension
The three versions of box counting algorithm for determining the fractal dimension of a spreadsheet Ms Excel is implemented. Values of Hearst exponent have been obtained for ten short individual time series, by the desig...
The examination of sentence and word length in the writing of Roman Ivanychuk
The article is dedicated to one of the most important areas of quantitative studies of language and speech that is the study of information and statistical properties of text. The length of sentences and words was calcul...
Efficiency Analysis of Wavelet Transform in Hidden Data Problems
Today embedding digital watermarks is one of the most effective means of protecting intellectual property. The paper made a comparative analysis of different wavelets, investigated under different coefficients of embeddi...