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

Heidari, Narges; Moradi, Parham; Koochari, Abbas

doi:10.1016/j.knosys.2022.109835

Cited by 33 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [27], dictionary learning is used to integrate the information of the trust and the rating matrix. [28] propose a deep learning-based method to solve the cold start and sparsity problems, which uses peripheral information to improve the matrix factorization process. They extract item information by processing their profiles and textual feature extraction and use it as a regularization term in the matrix factorization objective function.…”

Section: Related Workmentioning

confidence: 99%

A Framework for Accurate Recommendations and Explanation Generation Using Multi-Task Learning

Mansoorizadeh,

Shahidi,

Nazari

2023

Preprint

View full text Add to dashboard Cite

Recommendation systems predict desirable items for users based on their past interactions such as ratings, likes, and shopping history. However, these systems face challenges, including data insufficiency and lack of transparency. Leveraging user reviews has been proposed as a solution to address these challenges. User reviews serve as valuable supplementary data sources by conveying user preferences. Additionally, they provide a rich language source that can be used to generate textual explanations, thereby overcoming transparency issues. Therefore, this paper aims to utilize user reviews to enhance the accuracy of recommender systems and generate explanations for recommended items. These explanations help users understand various aspects of the recommended item from the perspective of real users. The use of textual explanations is prevalent in a wide range of explainable recommendation systems. However, previous works often overlook the writing style of users, which can significantly impact the effectiveness of explanations. Thus, the main objective of this paper is to develop a novel framework that incorporates user writing styles and preferences into the explanation generation process for recommendations. Results show that the developed multitask learning framework improves the accuracy of the recommendations. Furthermore, the generated explanations effectively support the induced recommendations.

show abstract

Section: Related Workmentioning

confidence: 99%

A Framework for Accurate Recommendations and Explanation Generation Using Multi-Task Learning

Mansoorizadeh,

Shahidi,

Nazari

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The challenge of cold start continues to be a dynamic and pertinent area of research, as extensively discussed by [24]. Notably, the authors have proposed the development of a language model autoencoder to effectively tackle the new user problem.…”

Section: Background and Related Workmentioning

confidence: 99%

Improving Cold Start Stereotype-Based Recommendation Using Deep Learning

Al-Rossais

2023

IEEE Access

View full text Add to dashboard Cite

Recommendation engines constitute a key component of many online platforms. One of the most challenging problems facing a recommender system is that of cold start, namely the recommendation of items from the catalogue to a new unknown user, or the recommendation of newly injected content to existing users. It is established that incorporating metadata describing the item or the user leads to better cold-start performance. Multiple independent findings point to the value of pre-processing the metadata to generate a new set of coordinates to aid the underlying recommendation algorithm; one of such pre-processing techniques, stereotyped features, has been shown to improve standard recommendation algorithms. Deep learning and complex neural networks have also been widely utilized in recent years in recommender systems, but their application and performance benchmarking in cold start scenarios is still a matter of ongoing research. This article reports on the application of deep learning neural networks to the stereotype driven framework for addressing cold start in recommender systems. We discuss the performance using a range of metrics, covering accuracy, and value content of ranked lists but also serendipity and fairness of recommendations, with the latter becoming an important metric and risk factor for the online platform offering the recommendations. Our findings indicate that a multi-layer neural network substantially improves cold start accuracy performance metrics, despite the recommendations displaying worse fairness and serendipity traits. The work discusses which metrics and scenarios still benefit from stereotyping features for the class of more sophisticated deep learning recommender systems.INDEX TERMS Cold start, deep learning, fairness of ranked lists, neural networks, new item problem, new user problem, recommender systems, recommender systems evaluation, serendipity of ranked lists, stereotypes.

show abstract

“…Numerous areas have successfully incorporated conventional recommender systems, for example, collaborative filtering (CF) and content-based (CB) techniques. These systems are crucial for recommending books on Amazon and videos on Netflix [9,10].…”

Section: Introductionmentioning

confidence: 99%

OntoCommerce: Incorporating Ontology and Sequential Pattern Mining for Personalized E-Commerce Recommendations

Mustafa,

Jhamat,

Arshad

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The abundance of information on online purchasing websites makes it challenging for customers to locate products that match their preferences. However, the cold-start problem arises when there isn't enough previous data, making it harder to make accurate recommendations for new customers or products. The enormous number of possible customers and products in a recommendation system leads to sparse data, which makes it harder to generate relevant recommendations and causes the sparsity problem. In addition, existing e-commerce recommender systems have difficulty making accurate product recommendations because they disregard individual consumer characteristics. In order to overcome these limitations, a hybrid recommender system combining ontology and sequential pattern mining (SPM) techniques is proposed. The strategy entails constructing an ontology that encompasses customer and product-related knowledge in the e-commerce domain. This ontology is then utilized to calculate customer preference similarities and generate predictions for the intended customer. The SPM algorithm is applied to the results of collaborative filtering to generate personalized recommendations for the customer. Experiments have demonstrated that the hybrid recommender system outperforms existing methods and resolves the cold-start problem and data sparsity in e-commerce recommender systems effectively. Even with limited initial data, the system generates accurate and individualized recommendations based on ontological domain knowledge and the customer's sequential purchase patterns. By integrating ontology and sequential pattern mining, this strategy enhances the precision and individualization of the e-commerce industry's recommendation process.

show abstract

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

Cited by 33 publications

References 56 publications

A Framework for Accurate Recommendations and Explanation Generation Using Multi-Task Learning

A Framework for Accurate Recommendations and Explanation Generation Using Multi-Task Learning

Improving Cold Start Stereotype-Based Recommendation Using Deep Learning

OntoCommerce: Incorporating Ontology and Sequential Pattern Mining for Personalized E-Commerce Recommendations

Contact Info

Product

Resources

About