Cold-start Problem Research Articles

An In-Depth Evaluation of Recommendation Systems: Methods, Challenges, and Solutions

Recommendation systems (RS) play a vital role in the digital landscape, in shaping user experiences across various platforms. It delves into the origins and key characteristics of Content-Based Filtering and Collaborative Filtering, backed by empirical analysis to underscore their practical significance. It will go through the intricate development stages of RS, spanning from data investigation to prediction methodologies, and tackles challenges such as the cold-start problem. RS is categorized into three main types: collaborative filtering, content-based filtering, and hybrid recommendation systems, highlighting their potential synergy in enhancing recommendation accuracy result and breadth. These insights lay the groundwork for subsequent, which explore evaluation techniques, seminal research, dataset analysis, and experimental findings, concluding with reflections and avenues for future research to advance the field of recommendation systems.

Hybrid Recommender Systems based on Content Feature Relationship

Recommendation systems get ever-increasing importance due to their applications in both academia and industry. The most popular type of these systems, known as collaborative filtering algorithms, employ user-item interactions to perform the recommendation tasks. With growth of additional information sources other than the rating (or purchase) history of users on items, such as item descriptions and social media information, further extensions of these systems have been proposed, known as hybrid recommendation algorithms. Hybrid recommenders use both user-item interaction data and their contextual information. In this work, we propose new hybrid recommender algorithms by considering the relationship between content features. This relationship is embedded into the hybrid recommenders to improve their accuracy. We first introduce a novel method to extract the content feature relationship matrix, and then the collaborative filtering recommender is modified such that this relationship matrix can be effectively integrated within the algorithm. The proposed algorithm can better deal with the cold-start problem than the state-of-art algorithms. We also propose a novel content-based hybrid recommender system. Our experiments on a benchmark movie dataset show that the proposed approach significantly improves the accuracy of the system, while resulting in satisfactory performance in terms of novelty and diversity of the recommendation lists.

Study on the effect of dissemination of Luo and Yue rice culture in multimedia technology-assisted rural cultural revitalization

Abstract Algorithmic recommendation is an important means of using multimedia technology for cultural dissemination and helping rural cultural revitalization. In order to realize the effective dissemination of Luo Yue rice culture, this paper constructs a hybrid recommendation algorithm that recommends videos about Luo Yue rice culture according to user preferences, which uses the cultural content relationship derived from LDA to replace the recommendation list generated by collaborative filtering and crosses it with the historical rating recommendation list to solve the problems of recommendation accuracy and cold start. The analysis of the dissemination effect shows that the average MAE value of this paper’s algorithm is 0.671, the proportion of users who watch relevant videos “occasionally” and more frequently has increased by 5.84%, and users recognize the recommendation method. The algorithm proposed in this paper has a good recommendation performance and helps to disseminate rural culture, as demonstrated by the above results.

A method for solving cold start problem using market basket analysis

A method for solving cold start problem using market basket analysis

A method for solving cold start problem using market basket analysis

A method for solving cold start problem using market basket analysis

Clustering-Based Frequent Pattern Mining Framework for Solving Cold-Start Problem in Recommender Systems

Clustering-Based Frequent Pattern Mining Framework for Solving Cold-Start Problem in Recommender Systems

SIIR: Symmetrical Information Interaction Modeling for News Recommendation.

Accurate matching between user and candidate news plays a fundamental role in news recommendation. Most existing studies capture fine-grained user interests through effective user modeling. Nevertheless, user interest representations are often extracted from multiple history news items, while candidate news representations are learned from specific news items. The asymmetry of information density causes invalid matching of user interests and candidate news, which severely affects the click-through rate prediction for specific candidate news. To resolve the problems mentioned above, we propose a symmetrical information interaction modeling for news recommendation (SIIR) in this article. We first design a light interactive attention network for user (LIAU) modeling to extract user interests related to the candidate news and reduce interference of noise effectively. LIAU overcomes the shortcomings of complex structure and high training costs of conventional interaction-based models and makes full use of domain-specific interest tendencies of users. We then propose a novel heterogeneous graph neural network (HGNN) to enhance candidate news representation through the potential relations among news. HGNN builds a candidate news enhancement scheme without user interaction to further facilitate accurate matching with user interests, which mitigates the cold-start problem effectively. Experiments on two realistic news datasets, i.e., MIND and Adressa, demonstrate that SIIR outperforms the state-of-the-art (SOTA) single-model methods by a large margin.

EduLGCL: Local-global contrastive learning model for education recommendation

Contrastive learning has been used in recommendations to learn user and item representations from sparse and long-tail user-item interaction histories. Recommendations applied in education have several key challenges. Firstly, the frequency of student-course interactions is lower, resulting in limited data. Secondly, existing models rely on multimodal data for multi-objective recommendations and they limit the model’s generalizability. Lastly, it is important to consider the impact of static features on different students. Aiming at addressing these challenges, a novel course recommendation system based on Local-Global Contrastive Learning called as EduLGCL is proposed, in which the mutual information between course features and student features is computed to select course features. After expanding the connections, the relationship between students and courses is described from different perspectives. Multiple graph convolutional operations are performed on the interaction history graph which can connect students and courses and represent student clusters. Through the feature extraction layer, the final student representation is obtained. Extensive experiments were conducted on three public datasets and a course dataset collected from a real-world environment to validate the performance of the EduLGCL. The results demonstrate that EduLGCL outperforms baseline methods, particularly in handling user cold-start problems. Our code is available at https://github.com/mintZYJ/EduLGCL.

Contrastive Multi-view Interest Learning for Cross-domain Sequential Recommendation

Cross-domain recommendation (CDR), which leverages information collected from other domains, has been empirically demonstrated to effectively alleviate data sparsity and cold-start problems encountered in traditional recommendation systems. However, current CDR methods, including those considering time information, do not jointly model the general and current interests within and across domains, which is pivotal for accurately predicting users’ future interactions. In this article, we propose a Contrastive learning-enhanced Multi-View interest learning model (CMVCDR) for cross-domain sequential recommendation. Specifically, we design a static view and a sequential view to model uses’ general interests and current interests, respectively. We divide a user’s general interest representation into a domain-invariant part and a domain-specific part. A cross-domain contrastive learning objective is introduced to impose constraints for optimizing these representations. In the sequential view, we first devise an attention mechanism guided by users’ domain-invariant interest representations to distill cross-domain knowledge pertaining to domain-invariant factors while reducing noise from irrelevant factors. We further design a domain-specific interest-guided temporal information aggregation mechanism to generate users’ current interest representations. Extensive experiments demonstrate the effectiveness of our proposed model compared with state-of-the-art methods.

MFM: A Multiple-Features Model for Leisure Event Recommendation in Geotagged Social Networks

Event-based social networks (EBSNs) are rich in information about users and leisure events. The willingness of users to participate in leisure events is influenced by many factors such as event time, location, content, organizer, and social relationship factors of users. Event recommendation systems in EBSNs can help leisure event organizers to accurately find users who want to participate in events. However, to address the existing cold-start problems and improve the accuracy of event recommendations, we propose a multiple-feature-based leisure event recommendation model (MFM). We introduce the user’s social contacts into the user preference features and construct a user feature space by integrating the features of the user preferences for events and organizers and preferences of the user’s closest friends. Moreover, considering the behavioral differences between active and inactive users, we extracted the respective features and trained the feature weight models. Finally, the experimental results showed that in comparison with the baseline models, the precision of the MFM is higher by at least 7.9%.

A content-based recommender system using stacked LSTM and an attention-based autoencoder

Recommender systems (RS) are popular in many areas, such as movies, music, news, books, research articles, search queries, and social tagging. Proprietary recommender systems are used by e-commerce websites like eBay, Amazon, and Alibaba to better match customers with products they are likely to purchase. This study suggests a recommender system that combines stacked long short-term memory (LSTM) and an attention-based autoencoder. This system would be used in a self-supervised learning paradigm, and the Amazon product datasets were used to run simulations. The results showed that the proposed method is more accurate, uses less computing power, and can be used on a large scale. No matter how big the data is, it can capture low-dimensional fixed latent representations and use the bare minimum of information already in the items, whether they are new or old. Several evaluation metrics show that the method works and that the cold start problem has been solved.

A Service Recommendation System Based on Dynamic User Groups and Reinforcement Learning

Recently, advancements in machine-learning technology have enabled platforms such as short video applications and e-commerce websites to accurately predict user behavior and cater to their interests. However, the limited nature of user data may compromise the accuracy of these recommendation systems. To address personalized recommendation challenges and adapt to changes in user preferences, reinforcement-learning algorithms have been developed. These algorithms strike a balance between exploring new items and exploiting existing ones, thereby enhancing recommendation accuracy. Nevertheless, the cold-start problem and data sparsity continue to impede the development of these recommendation systems. Hence, we proposed a joint-training algorithm that combined deep reinforcement learning with dynamic user groups. The goal was to capture user preferences for precise recommendations while addressing the challenges of data sparsity and cold-start. We used embedding layers to capture representations and make decisions before the reinforcement-learning process, executing this approach cyclically. Through this method, we dynamically obtained more accurate user and item representations and provide precise recommendations. Additionally, to address data sparsity, we introduced a dynamic user grouping algorithm that collectively enhanced the recommendations using group parameters. We evaluated our model using movie-rating and e-commerce datasets. As compared to other baseline algorithms, our algorithm not only improved recommendation accuracy but also enhanced diversity by uncovering recommendations across more categories.

A Social-aware Gaussian Pre-trained model for effective cold-start recommendation

The use of pre-training is an emerging technique to enhance a neural model’s performance, which has been shown to be effective for many neural language models such as BERT. This technique has also been used to enhance the performance of recommender systems. In such recommender systems, pre-training models are used to learn a better initialisation for both users and items. However, recent existing pre-trained recommender systems tend to only incorporate the user interaction data at the pre-training stage, making it difficult to deliver good recommendations, especially when the interaction data is sparse. To alleviate this rcommon data sparsity issue, we propose to pre-train the recommendation model not only with the interaction data but also with other available information such as the social relations among users, thereby providing the recommender rsystem with a better initialisation compared with solely relying on the ruser interaction data. We propose a novel recommendation model, the Social-aware Gaussian Pre-trained model (SGP), which encodes the user social relations and interaction data at the pre-training stage in a Graph Neural Network (GNN). Afterwards, in the subsequent fine-tuning stage, our SGP model adopts a Gaussian Mixture Model (GMM) to factorise these pre-trained embeddings for further training, thereby benefiting the cold-start users from these pre-built social relations. Our extensive experiments on three public datasets show that, in comparison to 16 competitive baselines, our SGP model significantly outperforms the best baseline by upto 7.7% in terms of NDCG@10. In addition, we show that SGP permits to effectively alleviate the cold-start problem, especially when users newly register to the system through their friends’ suggestions.

Overcoming cold start and sensor bias: A deep learning-based framework for IoT-enabled monitoring applications

Target localization is an essential aspect of smart environmental monitoring, which has gained prominence thanks to the Internet of Things (IoT) paradigm. Localization is the process of determining the location of an unknown target within an area of interest (AoI) based on data gathered by IoT sensors. Existing target localization works assume full knowledge about the sensors without considering the cold start problem, which may arise when new sensors join the network. This is exacerbated by the problem of bootstrapping in IoT sensors, where the system needs to identify and register unknown sensors. Additionally, the variability in sensors characteristics is inevitable due to the numerous factors that may alter the sensors behavior, raising the problem of sensor bias. Existing works dealing with the aforementioned problems are inadequate, since they involve a pre-processing step and assume the bias to be static over time, resulting in inaccurate localization systems. Therefore, this work proposes a robust and dynamic, holistic localization system that can find the location of an unknown emitting target regardless of the sensors characteristics. The proposed system comprises of two phases: 1) characterization and localization phase; where a deep learning model is utilized to characterize the sensors based on their locations and readings only, whereas Bayesian algorithm is employed to determine the unknown target location by leveraging the predicted sensors characteristics, and 2) correction phase, where an update metric is devised to refine the predicted sensors characteristics based on the estimated target location. The validation of the proposed approach was conducted using real-life and synthetic datasets and compared against an existing benchmark, where it shows an improvement of ∼79%, in terms of both localization and prediction errors. Thus, showcasing the effectiveness and potential advantages of the proposed approach in localizing unknown target(s).

Multi-Agent Reinforcement Learning Based File Caching Strategy in Mobile Edge Computing

Mobile edge computing (MEC) reduces data service latency by pushing data to the network edge. However, due to the dynamic and diverse requests of mobile users, the problem of mobile edge caching is more complex than cloud caching. Therefore, the existing model-based caching strategies cannot be directly used in the mobile edge caching environment. Besides, when taking the cooperative storage relationship between neighbor edge servers into consideration, the caching problem becomes more difficult. To this end, we formulate an mobile edge caching problem to minimize the total latency in mobile edge computing. Firstly, a heuristic caching strategy is proposed to solve the mobile edge caching problem in the single-time-slot scenario. Then, with the consideration of users’ mobility and the correlation of files, we propose a caching strategy for the multiple-time-slot scenario based on multi-agent deep reinforcement learning. To address the cold start problem in deep reinforcement learning, we adopt the proposed heuristic caching strategy used in the single-time-slot scenario to further optimize the training results. Extensive experiments on generated data and real-world datasets are conducted to verify that the proposed edge caching strategies can achieve the minimum latency compared with the state-of-the-art strategies.

A many objective commercial recommendation algorithm via Game-Based core node extraction

The development of the recommendation system (RS) has been focused on improving the accuracy of algorithms. As the number of new users grows, RS suffers from the cold start problem, data sparsity and long-tail problem. In this paper, we proposed a many objective commercial recommendation algorithm that extracts the core node through the pay-off function of game theory and makes it guide the evolutionary computation. Firstly, the core aim of commercial recommendations is to maximize total profit. Profits can vary wildly with the same accuracy. Thus, the profit value as one of the goals is considered in attention to accuracy, coverage, and novelty. Besides, the current user state value is updated according to user features and rating scores matrix with the attention mechanism at different time stamps. The nodes are divided into different communities, forming a dynamic community, and recommendations are made within each community. Meanwhile, to reduce the computational complexity and runtime, the pay-off function of game theory is used to extract the core user in each community. Each contribution value and user interaction as criteria to guide the current community of users. Experiments on real datasets show that selecting core nodes can improve the performance of business RS. Compared with other existing algorithms in many experiments, our algorithm performs better.

A Study of Reciprocal Job Recommendation for College Graduates Integrating Semantic Keyword Matching and Social Networking

With the surge in college graduate numbers, a disparity has emerged where the supply of jobs falls short of demand, intensifying employment pressures annually. College graduates, due to their lack of historical employment data compared with job seekers in the broader society, encounter a ‘cold start’ issue in the job recommendation process. Additionally, the nature of job recommendations, which differs fundamentally from unilateral recommendations, requires consideration of reciprocity between both parties involved. This article introduces a new approach to job recommendations using college graduates as the object of study. In the screening stage, a semantic keyword iterative algorithm is applied to compute the similarity between the resume and recruitment texts. This algorithm enhances the intersectionality of keywords in the calculation process, maximizing the utilization of resume information to enhance the accuracy of text similarity calculations. The ranking phase utilizes in-school data to build a social network between college graduates and graduated students and solves the system’s cold-start problem using the social network to recommend jobs for college graduates where graduated students are employed. We introduce a dual-dimensional matching approach that incorporates both specialty and salary, building upon the amalgamated semantic keyword iterative algorithm and the social network job recommendation method, to enhance the reciprocity of job recommendations. The job recommendation method introduced herein outperforms other methods in terms of the average satisfaction rate (AR) and normalized discounted cumulative gain (NDCG), thereby confirming its superior ability to meet the job-seeking preferences of graduates and the recruitment criteria of employers. This job recommendation method offers effective assistance to graduates lacking employment experience and historical employment data, facilitating their search for more suitable job opportunities.

Hybrid scientific article recommendation system with COOT optimization

Today, recommendation systems are everywhere, making a variety of activities considerably more manageable. These systems help users by personalizing their suggestions to their interests and needs. They can propose various goods, including music, courses, articles, agricultural products, fertilizers, books, movies, and foods. In the case of research articles, recommendation algorithms play an essential role in minimizing the time required for researchers to find relevant articles. Despite multiple challenges, these systems must solve serious issues such as the cold-start problem, article privacy, and changing user interests. This research addresses these issues through the use of two techniques: hybrid recommendation systems and COOT optimization. To generate article recommendations, a hybrid recommendation system integrates features from content-based and graph-based recommendation systems. COOT optimization is used to optimize the results, inspired by the movement of water birds. The proposed method combines a graph-based recommendation system with COOT optimization to increase accuracy and reduce result inaccuracies. When compared to the baseline approaches described, the model provided in this study improves precision by 2.3%, recall by 1.6%, and mean reciprocal rank (MRR) by 5.7%.

A Survey on Recommendation Methods Based on Social Relationships

With the rapid development of online social networks recently, more and more online users have participated in social network activities and rich social relationships are formed accordingly. These social relationships provide a rich data source and research basis for in-depth study on recommender systems (RSs), while also promoting the development of RSs based on social networks. To solve the problems of cold start and sparsity in RSs, many recommendation algorithms are constantly being proposed. Motivated by the availability of rich social connections in today’s RSs, a large number of recommendation techniques based on social relationships have been proposed recently, achieving good recommendation results, and have become the mainstream research direction in the field of RSs, attracting more and more researchers to engage in this research. In this study, we mainly review and summarize the social relationship-based recommendation methods and techniques in RSs, and study some recent deep social relationship recommendation methods and techniques based on deep learning (DL), including the latest social matrix factorization (MF)-based recommendation methods and graph neural network (GNN)-based recommendation methods. Finally, we discuss the potential impact that may improve the RS and future direction. In this article, we aim to introduce the recent recommendation techniques integrating social relationships to solve data sparsity and cold start, and provide a new perspective for improving the performance of RSs, thereby providing useful resources in the state-of-the-art research results for future researchers.

A Cluster-Aware Transfer Learning for Bayesian Optimization of Personalized Preference Models

Obtaining personalized models of the crowd is an important issue in various applications, such as preference acquisition and user interaction customization. However, the crowd setting, in which we assume we have little knowledge about the person, brings the cold start problem, which may cause avoidable unpreferable interactions with the people. This paper proposes a cluster-aware transfer learning method for the Bayesian optimization of personalized models. The proposed method, called Cluster-aware Bayesian Optimization, is designed based on a known feature: user preferences are not completely independent but can be divided into clusters. It exploits the clustering information to efficiently find the preference of the crowds while avoiding unpreferable interactions. The results of our extensive experiments with different data sets show that the method is efficient for finding the most preferable items and effective in reducing the number of unpreferable interactions.