User-item Matrix Research Articles

Addressing data sparsity and cold-start challenges in recommender systems using advanced deep learning and self-supervised learning techniques

ABSTRACT The efficacy of e-commerce conversion rates relies on precise and personalized product recommendations within recommendation systems (RS). While collaborative filtering-based RS has demonstrated success, challenges such as sparsity and cold-start issues in the user-item matrix can impede optimal functionality. To address these challenges, there is a need to integrate additional information sources, encompassing item/user profiles and textual reviews. This study introduces an innovative RS architecture that seamlessly combines self-supervised learning (SSL) and collaborative filtering techniques with BERT-DNN to surmount these obstacles. The distinctiveness of our approach lies in integrating self-supervised learning with collaborative filtering and contextualized data obtained from BERT-DNN, providing a profound understanding of item profiles to enhance comprehension of user preferences and item characteristics. This refined understanding, operational in conjunction with collaborative filtering models like ItemKNN and UserKNN, empowers the system to generate highly personalized recommendations. The proposed method entails several pivotal steps: developing the BERT language model for textual embeddings in item profiles, conducting dimensionality reduction, constructing a Deep Neural Network, implementing self-supervised learning with both UserKNN and ItemKNN CF methods, and employing an ensemble learning technique. Empirical results substantiate the efficacy of our approach, with a specific focus on the innovative fusion of BERT-DNN with self-supervised learning and KNN CF methodologies, showcasing substantial improvements across diverse performance metrics. This underscores the practical importance of leveraging contextualized BERT-DNN data, strengthening the recommendation mechanism, and ultimately enhancing the overall performance of the RS.

An autoencoder-based deep learning model for solving the sparsity issues of Multi-Criteria Recommender System

In recent times, recommender systems have acquired significant popularity as a solution to the issue of information overload. These systems offer personalised recommendations to users. The superiority of multi-criteria recommender systems over their single-criterion counterparts has been demonstrated, as the former are able to provide more precise recommendations by taking into account multiple dimensions of user preferences when rating items. The prevalent recommendation technique, matrix factorization of collaborative filtering, is hindered by the data sparsity problem of the user-item matrix. On the other hand, it is noteworthy that deep learning techniques have demonstrated significant potential in various research domains, including but not limited to image processing, pattern recognition, computer vision, and natural language processing. In recent times, there has been a surge in the utilisation of deep learning techniques in recommender systems, yielding promising outcomes. This study presents a novel approach to multi-criteria recommender systems through the utilisation of deep learning algorithms to mitigate the data sparsity issue. Specifically, deep autoencoders are utilised to uncover complex, non-linear, and latent relationships between users' multi-criteria preferences followed by matrix factorization technique, ultimately leading to more precise recommendations. The proposed model is evaluated by conducting the experiments on the multi-criteria dataset of Yahoo! Movies. According to the outcomes, the proposed approach outperforms the state of the art recommendation methods by generating more accurate and personalized recommendations. Also, it reduces the data sparsity up to 11% from the multi-criteria dataset.

Application of Methods of Recommendations in the Analysis of Computer Components

Today, the improvement of information and technical assistance to users through information technology is relevant. To improve the design of computers, we analyze its components and study the architecture, as well as the process of improving the functionality of a computer. We conducted an analytical review of existing software solutions for analyzing computer components. We consider models for forming a set of recommendations taking into account the wishes of the user. Given the specifics of the analysis of the problem situation, it is proposed to unite users into groups. Mixed categorical-numerical clustering was used to search for user groups. This took into account the numerical (Item ratings) and demographic properties of users, as well as the sparsity coefficient of the User-Item Matrix. His algorithm of operation of the hybrid recommendation system is described, which proposes to take into account the user's requirements when analyzing and generating component variability for a computer, a hybrid model of providing recommendations with a weighted weight factor is used. UML provides a conceptual model of the system. The recommendation system allows the user to use computer analysis of components, which will offer the best components and, most importantly, the most suitable details. If the user wants a completely new computer, he can use the assembly designer. Components will be selected for the user request, or a part of the computer will be offered. The target audience of the program is PC users of any age.

Metric Optimization and Mainstream Bias Mitigation in Recommender Systems

Recommender Systems have drawn extensive attention in recent decades. The most important factor to make a recommender succeed is user satisfaction, which is largely reflected by the recommendation accuracy. In accordance, this thesis dives into recommendation accuracy from two different perspectives that, unfortunately, are at tension with each other: achieving the maximum overall recommendation accuracy, and balancing that accuracy among all users. The first part of this thesis focuses on maximizing the overall recommendation accuracy Li et al. [2021a]. This accuracy is usually evaluated with some user-oriented metrics tailored to the recommendation scenario. However, recommendation models could be trained to maximize some other generic criteria that do not necessarily align with the criteria ultimately captured by the metric above. Recent research usually assumes that the metric used for evaluation is also the metric used for training. We challenge this assumption, mainly because some metrics are more informative than others. Indeed, we show that models trained via the optimization of a loss inspired by Rank-Biased Precision (RBP) tend to yield higher accuracy, even when accuracy is measured with metrics other than RBP. However, the superiority of this RBP-inspired loss stems from further benefiting users who are already well-served, rather than helping those who are not. This observation inspires the second part of this thesis, where our focus turns to helping nonmainstream users, who are difficult to recommend to either because of the lack of data for effective modeling or a niche taste that is hard to match similar users. Our first effort consists in using side data, beyond the user-item interaction matrix, so that users and items are better represented. This will be of benefit especially for the non-mainstream users, for which the user-item matrix alone is ineffective. We propose Neural AutoEncoder Collaborative Filtering (NAECF) Li et al. [2021b], an adversarial learning architecture that, in addition to maximizing the recommendation accuracy, leverages side data to preserve the intrinsic properties of users and items and show that NAECF leads to better recommendations specially for non-mainstream users, while at the same time there is a marginal loss for the mainstream ones. Our second effort Li et al. [2023] consists in explicitly focusing more on non-mainstream users in a recommendation model. In particular, we propose a mechanism based on cost-sensitive learning that weighs users according to their mainstreamness, so that they get more attention during training. The result is a recommendation model tailored to non-mainstream users, that narrows the accuracy gap, and again at negligible cost to the mainstream users. Awarded by : Delft University of Technology, Delft, The Netherlands on 14 November 2023. Supervised by : Alan Hanjalic and Julián Urbano. Available at : https://doi.org/10.4233/uuid:235a5f5c-5e18-4e67-a8e6-84a7e310db12.

A Survey of Sequential Pattern Based E-Commerce Recommendation Systems

E-commerce recommendation systems usually deal with massive customer sequential databases, such as historical purchase or click stream sequences. Recommendation systems’ accuracy can be improved if complex sequential patterns of user purchase behavior are learned by integrating sequential patterns of customer clicks and/or purchases into the user–item rating matrix input of collaborative filtering. This review focuses on algorithms of existing E-commerce recommendation systems that are sequential pattern-based. It provides a comprehensive and comparative performance analysis of these systems, exposing their methodologies, achievements, limitations, and potential for solving more important problems in this domain. The review shows that integrating sequential pattern mining of historical purchase and/or click sequences into a user–item matrix for collaborative filtering can (i) improve recommendation accuracy, (ii) reduce user–item rating data sparsity, (iii) increase the novelty rate of recommendations, and (iv) improve the scalability of recommendation systems.

Harnessing Item Features to Enhance Recommendation Quality of Collaborative Filtering

Recommendation systems provide ways of directing users to items that may be relevant to them by guiding them to relevant items that will be suitable to the users according to their profiles. Collaborative filtering is one of the most successful and mature techniques of recommender system because of its domain independent ability. Bayesian Personalized Ranking Smart Linear Model (BPRSLIM) is model-based collaborative filtering (CF) recommendation algorithm that usually reconstructs a scanty user-item matrix directly; also, using only user-rating matrix usually prevents the algorithm from accessing relevant information that could enhance its recommendation accuracy. Therefore, this work reconstructs BPRSLIM user-item rating matrix via item feature information in order to improve its performance accuracy. Comprehensive experiments were carried out on a real-world dataset using different evaluation metrics. The performance of the model showed significant improvement in recommendation accuracy when compared with other top-N collaborative filtering-based recommendation algorithms, especially in precision and nDCG with 30.6% and 22.1% respectively.

A Reliable Prediction Algorithm Based on Genre2Vec for Item-Side Cold-Start Problems in Recommender Systems with Smart Contracts

Personalized recommender systems are used not only in e-commerce companies but also in various web applications. These systems conventionally use collaborative filtering (CF) and content-based filtering approaches. CF operates using memory-based or model-based methods; both methods use a user-item matrix that considers user preferences as items. This matrix denotes information on user preferences, which refers to the user ratings for items. The model-based method exploits the fact that the input matrix is factorized. CF approaches can effectively provide personalized recommendation results to users; however, cold-start problems arise because both these methods depend on the users’ ratings for items to predict users’ preferences. We proposed an approach to alleviate the cold-start problem along with a methodology for utilizing blockchain that can enhance the reliability of the processes of the recommendations. We attempted to predict an average rating for a new item to alleviate item-side cold-start problems. First, we applied the concept of word2vec, treating each user’s item-selection history as a sentence. Then, we derived genre2Vec based on the skip-gram technique and predicted an average rating for a new item by utilizing the vectors and category ratings. We experimentally demonstrated that our approach could generate more accurate results than conventional CF approaches could. We also designed the processes of the recommendation based on the concept of blockchain addressing the smart contract. Based on our approach, we proposed a system that can secure reliability as well as alleviate the cold-start problems in recommender systems.

A proposed User-Based Approach for eBooks Recommendation Using a Weighted Nearest Neighbor Technique

Large book data stores were beneficial for our support systems but posed significant challenges for useful information retrieval. This issue was resolved by collaboratively filtering data depending on user needs. This study suggested a user-based methodology for recommending eBooks. The selected dataset was pre-processed, and Cross-validation was used to build a user-user similarity matrix. Three nearest neighbor algorithms (KNN Basic, KNN with Means and KNN with ZScore) were used, and weighted KNN was proposed for rating prediction. In this technique, the weight of each user was calculated based on its distance from the intended user. The evaluation process depends on the user-item matrix and user-user matrix for prediction. The proposed recommendation system was tested on the book-crossing dataset, and the results were evaluated using the root mean square error and the mean absolute value of error. The results show that the error rate of the proposed model is the lowest compared to the other methods used, specifically when using the Pearson-Baseline technique. Since the root mean square error is 1.647 and the mean absolute value of errors is 1.253. When using the cosine technique, the root mean square error is 1.742, and the mean absolute value of errors is 1.328.

Summarizing User-item Matrix By Group Utility Maximization

A user-item utility matrix represents the utility (or preference) associated with each (user, item) pair, such as citation counts, rating/vote on items or locations, and clicks on items. A high utility value indicates a strong association of the pair. In this work, we consider the problem of summarizing strong association for a large user-item matrix using a small summary size. Traditional techniques fail to distinguish user groups associated with different items (such as top- l item selection) or fail to focus on high utility (such as similarity- based subspace clustering and biclustering). We formulate a new problem, called Group Utility Maximization (GUM), to summarize the entire user population through k user groups and l items for each group; the goal is to maximize the total utility of selected items over all groups collectively. We show this problem is NP-hard even for l =1. We present two algorithms. One greedily finds the next group, called Greedy algorithm, and the other iteratively refines existing k groups, called k -max algorithm. Greedy algorithm provides the \((1-\frac{1}{e})\) approximation guarantee for a nonnegative utility matrix, whereas k -max algorithm is more efficient for large datasets. We evaluate these algorithms on real-life datasets.

Scalable and Data-Independent Multi-Agent Recommender System Using Social Networks Analysis

Nowadays, many online users find the selection of information and required products challenging due to the growing volume of data on the web. Recommender systems are introduced to deal with information overload. Cold start and data sparsity are the two primary issues in these systems, which lead to a decrease in the efficiency of recommender systems. To solve the problems, this paper proposes a novel method based on social network analysis. Our method leverages a multi-agent system for clustering users and items and predicting relationships between them simultaneously. The information on users and items is extracted from the user-item matrix as distinct graphs. Each of the graphs is then treated as a social network, which is further processed and analyzed by community detection and link prediction procedures. The users are grouped into several clusters by the community detection agent, which results in each cluster as a community. Then link prediction agent identifies the latent relationships between users and items. Simulation results show that the proposed method has significantly improved performance metrics as compared to recent techniques.

Improving Data Sparsity in Recommender Systems Using Matrix Regeneration with Item Features

With the development of the Web, users spend more time accessing information that they seek. As a result, recommendation systems have emerged to provide users with preferred contents by filtering abundant information, along with providing means of exposing search results to users more effectively. These recommendation systems operate based on the user reactions to items or on the various user or item features. It is known that recommendation results based on sparse datasets are less reliable because recommender systems operate according to user responses. Thus, we propose a method to improve the dataset sparsity and increase the accuracy of the prediction results by using item features with user responses. A method based on the content-based filtering concept is proposed to extract category rates from the user–item matrix according to the user preferences and to organize these into vectors. Thereafter, we present a method to filter the user–item matrix using the extracted vectors and to regenerate the input matrix for collaborative filtering (CF). We compare the prediction results of our approach and conventional CF using the mean absolute error and root mean square error. Moreover, we calculate the sparsity of the regenerated matrix and the existing input matrix, and demonstrate that the regenerated matrix is more dense than the existing one. By computing the Jaccard similarity between the item sets in the regenerated and existing matrices, we verify the matrix distinctions. The results of the proposed methods confirm that if the regenerated matrix is used as the CF input, a denser matrix with higher predictive accuracy can be constructed than when using conventional methods. The validity of the proposed method was verified by analyzing the effect of the input matrix composed of high average ratings on the CF prediction performance. The low sparsity and high prediction accuracy of the proposed method are verified by comparisons with the results by conventional methods. Improvements of approximately 16% based on K-nearest neighbor and 15% based on singular value decomposition, and a three times improvement in the sparsity based on regenerated and original matrices are obtained. We propose a matrix reconstruction method that can improve the performance of recommendations.

An attention-based deep learning method for solving the cold-start and sparsity issues of recommender systems

Matrix Factorization is a successful approach for generating an effective recommender system. However, most existing matrix factorization methods suffer from the sparsity and cold-start issues of the user-item matrix as the primary information source of recommender systems. Besides, they are not much scalable to apply to large real-world applications. A main idea to overcome the cold-start and sparsity issues is to use additional information sources such as user/item profiles or user reviews on items. In this paper, a novel Attention-based Deep Learning Recommender System, so-called ADLRS, is proposed to employ the information sources in the matrix factorization method framework. The proposed method uses a language model to represent contextual information such that important features are effectively embedded. Moreover, a deep autoencoder reduces the dimensionality of item vectors embedded by the language model. Then, these vectors are used as regularization terms in the matrix factorization framework to form an objective function. Then, an iterative algorithm is designed to solve the objective function and provide a method prediction of unknown rating values. Experimental results show that the proposed method achieves superior performance compared to other state-of-the-art ones in most cases. Moreover, the improvement rate for sparse datasets and cold items proves that the proposed method effectively deals with sparsity, cold start and scalability problems.

Incorporating a Topic Model into a Hypergraph Neural Network for Searching-Scenario Oriented Recommendations

The personalized recommendation system is a useful tool adopted by e-retailers to help consumers to find items in line with their preferences. Existing methods focus on learning user preferences from a user-item matrix or online reviews after purchasing, and they ignore the interactive features in the process of users’ learning about product information through search queries before they make a purchase. To this end, this study develops a topic augmented hypergraph neural network framework to predict the user’s purchase intention by connecting the latent topics embedded in a consumer’s online queries to their click, purchase, and online review behavior, which aims at mining the connection information existing in the interaction graph domain. Meanwhile, in order to reduce the influence of text noise words by fusing topic information, we integrate the topic distribution and convolutional embedding to better represent each user and item, which can make up for the lack of topic information in traditional convolutional neural networks. Extensive empirical evaluations on real-world datasets demonstrate that the proposed framework improves the novelty of recommendation items as well as accuracy. From a managerial perspective, recommending diversified and novel items to consumers may increase the users’ satisfaction, which is conducive to the sustainable development of e-commerce enterprises.

Fidelity Homogenous Genesis Recommendation Model for User Trust with Item Ratings

Abstract The ever-increasing volume of cloud services has created a service targeting issue. The mechanisms of recommenders address the issue by allowing consumers to easily access services that match their preferences. A recommendation is a regularly utilized function in recommender systems to assist users in swiftly narrowing their choices and making sensible judgments from a large amount of knowledge. In this document, design a “Fidelity Homogenous Genesis Recommendation Model” for user trust along with item ratings. The key for addressing data sparsity is how accurately the likely values of unoccupied cells are estimated. For sparsity reduction of the user-item matrix, we employ a similar prior case rationale technique mixed with average filling. This phase will aid in the later computation of user and item similarity. Genesis: the autonomous map technique was used to clustering the user-item matrix for similar users, followed by an optimization process to generate sub-optimal clusters with a more balanced number of users in each. Based on actual grid computing, the User-Item Privacy Marmalade Technique considers all trustworthy neighbors to be available after optimization. Based on the filtered item set, the trust weighting approach is intended to compute trust similarity among users. To locate trustworthy users, the filtered item set traverses all users in trust networks. In particular, a user trust neighbor set that has comparable preferences and matches with a target user and can be derived through user trust dispersion features in a trusted network. As a result, the proposed algorithm was able to give a novel recommendation model that was guided by user trust as well as item ratings.

A novel temporal recommendation method based on user query topic evolution

Personalized product recommendation provides online customers with options in line with consumers’ interests and preferences to assist users in making purchasing decisions. Previous personalized recommendation methods identify user preferences by analyzing historical purchase data. As the user preferences reflected in the user–item matrix take only two values: like or dislike, the binary purchase data-based method is too constrained to capture individual diverse opinions and user preferences evolution. Despite the fact that online search queries explicitly express consumers’ content preferences for product attributes, very little research has focused on inferring user preferences from online queries. To this end, this study proposes a novel temporal recommendation method based on estimating consumers’ dynamic preferences from their search queries. Our approach involves: first, proposing a temporal topic model that utilizes a Markov process to predict users’ potential interests, and then integrating customer preferences and product attribute features into a unified product ranking model to obtain personalized and diversified product lists. Empirical analysis shows that the proposed approach can better capture the temporal dynamics of customer preferences drift and can more accurately predict consumer purchase intentions. Furthermore, products recommended by the proposed approach not only better match individual preferences, but also cover more diverse content topics.

Hybrid recommendation algorithm based on real-valued RBM and CNN.

With the unprecedented development of big data, it is becoming hard to get the valuable information hence, the recommendation system is becoming more and more popular. When the limited Boltzmann machine is used for collaborative filtering, only the scoring matrix is considered, and the influence of the item content, the user characteristics and the user evaluation content on the predicted score is not considered. To solve this problem, the modified hybrid recommendation algorithm based on Gaussian restricted Boltzmann machine is proposed in the paper. The user text information and the item text information are input to the embedding layer to change the text information into numerical vector. The convolutional neural network is used to get the latent feature vector of the text information. The latent vector is connected to rating vector to get the item and the user vector. The user vector and the item vector are fused together to get the user-item matrix which is input to the visual layer of Gaussian restricted Boltzmann Machine to predict the ratings. Some simulation experiments have been performed on the algorithm, and the results of the experiments proved that the algorithm is feasible.

Algorithms for the Formation of Recommendations in the Information System

The article deals with the problem of scalability and dimension reduction of data in the algorithms of recommendations. It is proposed to improve the item-to-item algorithm by excluding from the user-item matrix elements that that do not have enough estimates. Thus more denser data are used that allows to receive more exact results. Also due to the fact that the dimension of the user-item matrix decreases, the execution time of the algorithm decreases. To solve the problem, the Tachimoto coefficient, the cosine measure, the Pearson correlation coefficient and the Euclidean distance are used to calculate the degree of similarity of the elements. The efficiency of the usual item-to-item algorithm and the algorithm were compared using only the active values in the user-item matrix. The obtained results confirm the efficiency of the item-to-item algorithm based on a dense matrix. The obtained results can be used to optimize the operation of any recommendation system.

A hybrid recommender system based on data enrichment on the ontology modelling

Background: A recommender system captures the user preferences and behaviour to provide a relevant recommendation to the user. In a hybrid model-based recommender system, it requires a pre-trained data model to generate recommendations for a user. Ontology helps to represent the semantic information and relationships to model the expressivity and linkage among the data. Methods: We enhanced the matrix factorization model accuracy by utilizing ontology to enrich the information of the user-item matrix by integrating the item-based and user-based collaborative filtering techniques. In particular, the combination of enriched data, which consists of semantic similarity together with rating pattern, will help to reduce the cold start problem in the model-based recommender system. When the new user or item first coming into the system, we have the user demographic or item profile that linked to our ontology. Thus, semantic similarity can be calculated during the item-based and user-based collaborating filtering process. The item-based and user-based filtering process are used to predict the unknown rating of the original matrix. Results: Experimental evaluations have been carried out on the MovieLens 100k dataset to demonstrate the accuracy rate of our proposed approach as compared to the baseline method using (i) Singular Value Decomposition (SVD) and (ii) combination of item-based collaborative filtering technique with SVD. Experimental results demonstrated that our proposed method has reduced the data sparsity from 0.9542% to 0.8435%. In addition, it also indicated that our proposed method has achieved better accuracy with Root Mean Square Error (RMSE) of 0.9298, as compared to the baseline method (RMSE: 0.9642) and the existing method (RMSE: 0.9492). Conclusions: Our proposed method enhanced the dataset information by integrating user-based and item-based collaborative filtering techniques. The experiment results shows that our system has reduced the data sparsity and has better accuracy as compared to baseline method and existing method.

An E-Commerce Recommendation System Based on Dynamic Analysis of Customer Behavior

The technological development in the devices and services provided via the Internet and the availability of modern devices and their advanced applications, for most people, have led to an increase in the expansion and a trend towards electronic commerce. The large number and variety of goods offered on e-commerce websites sometimes make the customers feel overwhelmed and sometimes make it difficult to find the right product. These factors increase the amount of competition between global commercial sites, which increases the need to work efficiently to increase financial profits. The recommendation systems aim to improve the e-commerce systems performance by facilitating the customers to find the appropriate products according to their preferences. There are lots of recommendation system algorithms that are implemented for this purpose. However, most of these algorithms suffer from several problems, including: cold start, sparsity of user-item matrix, scalability, and changes in user interest. This paper aims to develop a recommendation system to solve the problems mentioned before and to achieve high realistic prediction results this is done by building the system based on the customers’ behavior and cooperating with the statistical analysis to support decision making, to be employed on an e-commerce site and increasing its performance. The project contribution can be shown by the experimental results using precision, recall, F-function, mean absolute error (MAE), and root mean square error (RMSE) metrics, which are used to evaluate system performance. The experimental results showed that using statistical methods improves the decision-making that is employed to increase the accuracy of recommendation lists suggested to the customers.

A hybrid recommender system based on data enrichment on the ontology modelling.

Background: A recommender system captures the user preferences and behaviour to provide a relevant recommendation to the user. In a hybrid model-based recommender system, it requires a pre-trained data model to generate recommendations for a user. Ontology helps to represent the semantic information and relationships to model theexpressivity and linkage among the data. Methods: We enhanced the matrix factorization model accuracy by utilizing ontology to enrich the information of the user-item matrix by integrating the item-based and user-based collaborative filtering techniques. In particular, the combination of enriched data, which consists of semantic similarity together with rating pattern, will help to reduce the cold start problem in the model-based recommender system. When the new user or item first coming into the system, we have the user demographic or item profile that linked to our ontology. Thus, semantic similarity can be calculated during the item-based and user-based collaborating filtering process. The item-based and user-based filtering process are used to predict the unknown rating of the original matrix. Results: Experimental evaluations have been carried out onthe MovieLens 100k dataset to demonstrate the accuracy rate of our proposed approach as compared to the baseline methodusing (i) Singular Value Decomposition (SVD) and (ii) combination of item-based collaborative filtering technique with SVD. Experimental results demonstrated thatour proposed method has reduced the data sparsity from 0.9542% to 0.8435%. In addition, it also indicated that our proposed method has achieved better accuracy with Root Mean Square Error (RMSE) of 0.9298, as compared to the baseline method (RMSE: 0.9642) and the existing method (RMSE:0.9492). Conclusions: Our proposed method enhanced the dataset information by integrating user-based and item-based collaborative filtering techniques. The experiment results shows that our system has reduced the data sparsity and has better accuracy as compared to baseline method and existing method.