Latent based temporal optimization approach for improving the performance of collaborative filtering

Abstract

Recommendation systems suggest peculiar products to customers based on their past ratings, preferences, and interests. These systems typically utilize collaborative filtering (CF) to analyze customers’ ratings for products within the rating matrix. CF suffers from the sparsity problem because a large number of rating grades are not accurately determined. Various prediction approaches have been used to solve this problem by learning its latent and temporal factors. A few other challenges such as latent feedback learning, customers’ drifting interests, overfitting, and the popularity decay of products over time have also been addressed. Existing works have typically deployed either short or long temporal representation for addressing the recommendation system issues. Although each effort improves on the accuracy of its respective benchmark, an integrative solution that could address all the problems without trading off its accuracy is needed. Thus, this paper presents a Latent-based Temporal Optimization (LTO) approach to improve the prediction accuracy of CF by learning the past attitudes of users and their interests over time. Experimental results show that the LTO approach efficiently improves the prediction accuracy of CF compared to the benchmark schemes.

Improving patient rehabilitation performance in exercise games using collaborative filtering approach

“…BFOA is one of the efficient optimisation algorithms that have been used in improving the prediction performance of the CF technique in some recommendation systems ( Al-Hadi et al, 2020b , 2017 ). Accordingly, BFOA is utilized in the ReComS++ approach for reducing the overfitted prediction values by learning the latent features of the neighbours within each cluster.…”

“…This function provides the correlation between the target record (of game and movement) and total records. The similarity functions that apply the CF technique are Cosine Similarity ( Al-Hadi et al, 2020b ) and the Pearson Correlation Coefficient ( Srifi et al, 2020 ). Note that when using the Cosine or Correlation coefficient for MIRA data, these functions generate some outliers due to the existence of zeros in the feature matrix.…”

“…Optimisation algorithms have proven effective in several areas including RS ( Al-Hadi et al, 2017 ) and healthcare ( Zainal et al, 2020 ). For instance, BFOA has been well-embraced in recent RS approaches for providing high accuracy prediction ( Al-Hadi et al, 2020b , 2017 ). This motivates us to use BFOA in this experiment for learning patients’ latent features and for optimising the output prediction.…”

Natural Language Processing for Analyzing Online Customer Reviews: A Survey, Taxonomy, and Open Research Challenges

“…Analyzing social media comments using NLP, the study identified triggers for the Amazon effect, highlighting widespread dissatisfaction and reduced satisfaction with other retailers influenced by elevated consumer expectations shaped by Amazon [158]. The study on CF recommendation systems utilized sentiment analysis on user reviews to derive implicit ratings, introducing novel approaches that demonstrated effectiveness in enhancing CF performance [159].…”

“…Explored the impact of the 'Amazon effect' on consumer perceptions of service attributes in Italian consumer electronics retailers. [159] Amazon, Yelp Introduced CF methods leveraging sentiment analysis on user reviews. [160] Amazon Introduced a novel TADO model for review-based recommender systems.…”