Exploiting Past Users’ Interests and Predictions in an Active Learning Method for Dealing with Cold Start in Recommender Systems

Abstract

This paper focuses on the new users cold-start issue in the context of recommender systems. New users who do not receive pertinent recommendations may abandon the system. In order to cope with this issue, we use active learning techniques. These methods engage the new users to interact with the system by presenting them with a questionnaire that aims to understand their preferences to the related items. In this paper, we propose an active learning technique that exploits past users’ interests and past users’ predictions in order to identify the best questions to ask. Our technique achieves a better performance in terms of precision (RMSE), which leads to learn the users’ preferences in less questions. The experimentations were carried out in a small and public dataset to prove the applicability for handling cold start issues.

Investigation of Combining Logitboost(M5P) under Active Learning Classification Tasks

“…where more details are provided in [35]. A quite important research orientation of the related community is the proposal of a new QS, either introducing new metrics which may measure a behavior that seems more favorable for specific tasks [36,37] or trying to capture better the reasoning of some choices made by similar methods [38]. One representative work related to this last category is the work of Vu-Linh Nguyen et al [39], exploring further Uncertainty Sampling (UncS) QS, discriminating this into epistemic and aleatoric sampling strategies, highlighting their differences and proposing the first variant as more promising.…”

Improving Personalized Questionnaire With Redundancy Reduction for Addressing Cold User Problem

“…We have presented in this section a review to our work. Pozo et al (2018) worked on a personalized questionnaire approach of solving cold start problem. The researcher realized that when a new user is not recommended items of his choice, the user might choses to restrain the recommendation system.…”

“…Reference SUMMARY (Pozo, 2018) Pozo( 2018) worked on a personalized questionnaire approach of solving cold start problem. The researcher address cold user problem by presenting personalized questionnaire to a new user purposely capture the new user's interest.…”

“…From figure1 we can clearly see that the most used algorithms are matrix factorization algorithm and Pearson correlation algorithm with the percentage of 30% and 13.25% respectively. Most active learning techniques implementation are implemented using decision tree algorithm (Pozo et al, 2018). We present the basic steps involved in decision tree algorithm in Algorithm1, and below it are the basic steps involved in Pearson correlation algorithm in Algorithm 2.…”

“…A new user is presented personalized questionnaire so that his/ her interest could be acquired, and then the result of the personalized questionnaire is used to determine which cluster to place the new user so that recommendations are provided to him as though he/she is an existing user (Smith et al, 2019). Unfortunately, the techniques of administering personalized questionnaires could be effective in situations where database of product is not too large (Pozo et al, 2018). Uncertainty reduction technique is also another technique applied in addressing cold user problem (Nadimi-Shahraki and Bahadorpour, 2014;Karimi et al, 2011).…”