scholarly journals Modeling the user’s choice in the constraints of the cold start of the recommender system.

2019 ◽  
Vol 1 (92) ◽  
pp. 14-19
Author(s):  
V.O. Leshchynskyi ◽  
I.O. Leshchynska
Keyword(s):  
Recommender System ◽  
Consumer Choice ◽  
Input Data ◽  
Operation Mode ◽  
Cold Start ◽  
Normal Operation ◽  
Time Interval ◽  
Problem Structuring ◽  
Object A ◽  
Object Selection

The problem of supporting user choice in recommender systems is considered, taking into accountthe limitations that arise when solving a cold start problem. Structuring of this problem was carried out and suchaspects of a cold start were highlighted as the emergence of a new user, the emergence of a new consumer interest object, a change in the user selection context, a change in consumer interests over time. A system-oriented model of object selection in the normal operation mode of the recommender system was proposed, as well as a model-oriented model of object selection under cold start conditions. Restrictions in the proposed models are presented in the form of predicates on variables that characterize the properties of consumers and objects of theirinterest, as well as the context of consumer choice. The advantage of the proposed models is the ability to limit the input data, so that they correspond to the most significant laws of consumer choice in this context at a given time interval, which allows us to simplify the construction of recommendations for new consumers and new objects. An approach to building recommendations in the context of cold start restrictions is proposed. The approach assumes the formation of constraints based on the intellectual analysis of the input data of the recommender system, as well as the further use of these constraints in constructing recommendations in cold start conditions.

Modelling trust networks using resistive circuits for trust-aware recommender systems

2016 ◽  
Vol 43 (1) ◽  
pp. 135-144 ◽  
Author(s):  
Mehdi Hosseinzadeh Aghdam ◽  
Morteza Analoui ◽  
Peyman Kabiri
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Cold Start ◽  
User Preferences ◽  
Item Selection ◽  
Trust Networks ◽  
Trust Inference ◽  
Trust Information

Recommender systems have been widely used for predicting unknown ratings. Collaborative filtering as a recommendation technique uses known ratings for predicting user preferences in the item selection. However, current collaborative filtering methods cannot distinguish malicious users from unknown users. Also, they have serious drawbacks in generating ratings for cold-start users. Trust networks among recommender systems have been proved beneficial to improve the quality and number of predictions. This paper proposes an improved trust-aware recommender system that uses resistive circuits for trust inference. This method uses trust information to produce personalized recommendations. The result of evaluating the proposed method on Epinions dataset shows that this method can significantly improve the accuracy of recommender systems while not reducing the coverage of recommender systems.

scholarly journals Tag-Aware Recommender System Based on Deep Reinforcement Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Zhiruo Zhao ◽  
Xiliang Chen ◽  
Zhixiong Xu ◽  
Lei Cao
Keyword(s):  
Reinforcement Learning ◽  
Recommender System ◽  
Complex Function ◽  
Cold Start ◽  
Sparse Data ◽  
Excellent Performance ◽  
Minimum Error ◽  
Reward Function ◽  
Function Design

Recently, the application of deep reinforcement learning in the recommender system is flourishing and stands out by overcoming drawbacks of traditional methods and achieving high recommendation quality. The dynamics, long-term returns, and sparse data issues in the recommender system have been effectively solved. But the application of deep reinforcement learning brings problems of interpretability, overfitting, complex reward function design, and user cold start. This study proposed a tag-aware recommender system based on deep reinforcement learning without complex function design, taking advantage of tags to make up for the interpretability problems existing in the recommender system. Our experiment is carried out on the MovieLens dataset. The result shows that the DRL-based recommender system is superior than traditional algorithms in minimum error, and the application of tags have little effect on accuracy when making up for interpretability. In addition, the DRL-based recommender system has excellent performance on user cold start problems.

scholarly journals METHOD FOR DETECTING SHILLING ATTACKS BASED ON IMPLICIT FEEDBACK IN RECOMMENDER SYSTEMS

2020 ◽  
Vol 5 ◽  
pp. 21-30
Author(s):  
Oksana Chala ◽  
Lyudmyla Novikova ◽  
Larysa Chernyshova ◽  
Angelika Kalnitskaya
Keyword(s):  
Recommender System ◽  
Input Data ◽  
Implicit Feedback ◽  
User Selection ◽  
Time Intervals ◽  
User Interests ◽  
Selection Processes ◽  
Key Characteristics ◽  
The Relationship ◽  
Explicit Feedback

The problem of identifying shilling attacks, which are aimed at forming false ratings of objects in the recommender system, is considered. The purpose of such attacks is to include in the recommended list of items the goods specified by the attacking user. The recommendations obtained as a result of the attack will not correspond to customers' real preferences, which can lead to distrust of the recommender system and a drop in sales. The existing methods for detecting shilling attacks use explicit feedback from the user and are focused primarily on building patterns that describe the key characteristics of the attack. However, such patterns only partially take into account the dynamics of user interests. A method for detecting shilling attacks using implicit feedback is proposed by comparing the temporal description of user selection processes and ratings. Models of such processes are formed using a set of weighted temporal rules that define the relationship in time between the moments when users select a given object. The method uses time-ordered input data. The method includes the stages of forming sets of weighted temporal rules for describing sales processes and creating ratings, calculating a set of ratings for these processes, and forming attack indicators based on a comparison of the ratings obtained. The resulting signs make it possible to distinguish between nuke and push attacks. The method is designed to identify discrepancies in the dynamics of purchases and ratings, even in the absence of rating values at certain time intervals. The technique makes it possible to identify an approach to masking an attack based on a comparison of the rating values and the received attack indicators. When applied iteratively, the method allows to refine the list of profiles of potential attackers. The technique can be used in conjunction with pattern-oriented approaches to identifying shilling attacks

scholarly journals A DNN-Based Cross-Domain Recommender System for Alleviating Cold-Start Problem in E-Commerce

2020 ◽  
Vol 1 ◽  
pp. 194-206
Author(s):  
Hanxin Wang ◽  
Daichi Amagata ◽  
Takuya Makeawa ◽  
Takahiro Hara ◽  
Niu Hao ◽  
...  
Keyword(s):  
Recommender System ◽  
Cold Start ◽  
Cross Domain ◽  
Cold Start Problem
Sign in / Sign up

Export Citation Format

Share Document