Cold-start Problem Research Articles

A Novel News Recommendation Model With Knowledge Enhancement and Stability

With the rapid development of information technology, today’s society has higher and higher requirements for the recommendation system, especially regarding recommendation accuracy. A significant feature of news recommendation is that it has high timeliness, and the popularity of a news article will decline exponentially in a week. The effectiveness of traditional recommendation methods in news recommendation could be more optimistic. In order to further improve the accuracy of news recommendations, a large number of knowledge graphs are applied to news recommendations, and the nodes and edges of the knowledge graph can better represent the relationship between entities in the article; compared with traditional recommendation methods, it can better solve the problems of data sparsity and cold start. This paper proposes a relational entity credibility discrimination model, eliminating the relational entities without credibility to improve news recommendations accuracy, the existence of some relational entities in the triad of the knowledge graph may distort the meaning of the article or have a near-zero impact on the article, which is considered untrustworthy for these two types of relational entities. Experimental results show the effectiveness and efficiency of the model.

Attempted Improvements on Existing Recommendation System

This paper presents an exploration and enhancement of existing recommendation systems by addressing key challenges such as the cold-start problem and data sparsity. We propose DGSR++, a hybrid model that combines dynamic user-item interaction data with content-based features to enhance recommendation quality. Additionally, we develop MPKG lite, a lightweight knowledge graph embedding model, to mitigate cold-start issues. Besides, we also improved other models, such as GTN and ensembled learning. The paper also evaluates the performance of ensemble learning methods. Experimental results demonstrate the priority of DGSR++ in solving cold-start challenges and improving overall recommendation accuracy compared to traditional approaches.

Improved recommender system using Neural Network Collaborative Filtering (NNCF) for E-commerce cosmetic product

This study presents an enhanced recommender system tailored for e-commerce platforms specializing in cosmetic products. Traditional recommender systems often need help providing accurate and personalized recommendations due to the complexity and subjectivity inherent in cosmetic preferences. In e-commerce, personalized product recommendations are crucial to improving user engagement and driving sales. This paper presents an innovative approach to enhance recommendation systems by leveraging neural network collaborative filtering techniques for the cosmetic product domain. The proposed method integrates neural networks into collaborative filtering, namely neural network collaborative filtering with improved preprocessing step. To validate the effectiveness of our proposed system, extensive experiments were conducted using real-world e-commerce cosmetic datasets "eCommerce Event History in Cosmetics Shop". Additionally, we evaluate the system's performance using historical e-commerce event data in cosmetics stores, demonstrating the system's effectiveness with mean reciprocal ratings (MRR) and normalized discount cumulative gain (NDCG). Evaluation Metrics of MRR and NDCG in this study got 0.56 and 0.60, respectively, with a split of the data: 70% train data, 15% validation data, and 15% test data. This study obtained better evaluation metrics than the previous study, which had an MRR of 0.31 and NDGC of 0.32. Furthermore, this model exhibits robustness against data sparsity and cold-start problems commonly encountered in e-commerce platforms. This research advances knowledge of recommendation systems and paves the way for more personalized and efficient online shopping experiences.

Research on Music Content Identification and Recommendation Technology Based on Deep Learning

This research introduces a novel music recommendation system leveraging deep learning techniques to tackle significant challenges in traditional recommendation methods, such as the cold start problem, limited recommendation diversity, and difficulty in adapting to evolving user preferences. The proposed model employs Convolutional Neural Networks (CNNs) for genre recognition, coupled with Harmonic-Percussive Source Separation (HPSS) to extract rich audio features, capturing intricate musical distinctions across genres. These features, combined with user interaction data, enable the model to deliver highly personalized recommendations based on individual listening habits. Experimental results show that the system significantly outperforms conventional approaches, with a genre classification accuracy of 92%, offering greater recommendation accuracy and diversity. This marks a substantial improvement over traditional collaborative filtering and content-based methods, which struggle to deliver relevant suggestions in dynamic user environments. The findings highlight that deep learning, particularly CNNs, can effectively overcome data sparsity issues and provide more adaptive, user-centered recommendations. Moreover, the system's ability to integrate real-time user interaction data leads to enhanced user engagement, as the recommendations become more relevant and aligned with individual preferences. Future work will explore enhancing the dataset's diversity and optimizing computational efficiency to support scalability, ensuring the model can be applied across different cultures and regions. By improving the model's adaptability and efficiency, this research aims to create a more inclusive and scalable music recommendation system, capable of catering to global audiences with diverse musical tastes. Ultimately, the proposed system contributes to the development of more accurate, personalized, and engaging music recommendation frameworks, marking a significant advancement in the field of music information retrieval.

A concise review of developments to overcome the cold start problems by analyzing combustion and emissions of methanol-based-fueled spark ignition engines

A concise review of developments to overcome the cold start problems by analyzing combustion and emissions of methanol-based-fueled spark ignition engines

Construction of College Students’ Music Interest Platform Based on Internet+

In the context of the gradual improvement of the degree of personalized development, College Students’ interest in music shows a diversified trend, which makes the construction of relevant music platforms fully consider the actual needs of individual users and recommend resources corresponding to their interests. This paper puts forward the research on the construction of College Students’ music interest platform based on Internet [Formula: see text]. On the premise of analyzing the value proposition of the cultural industry platform model and the emphasis on customer goals under the background of “Internet [Formula: see text]”, this paper designs a platform structure including resource management module, College Students’ user management module, resource recommendation module and resource startup module. The big data technology under the background of “Internet [Formula: see text]” is used to analyze the MIDI audio characteristics and user behavior characteristics of resources. The binary community is used to establish the matching relationship between the two, determine the recommended resources, and introduce the heat parameter to avoid the cold start problem. The test results show that the processing efficiency and response time of the design platform for user behavior and user requests can meet the needs of practical applications, and has high stability. The collection map, Download map and share map of the recommended results of the platform are the best outputs in the test stage.

SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering

With the flourishing of social media platforms, data in social networks, especially user-generated content, are growing rapidly, which makes it hard for users to select relevant content from the overloaded data. Recommender systems are thus developed to filter user-relevant content for better user experiences and also the commercial needs of social platform providers. Graph neural networks have been widely applied in recommender systems for better recommendation based on past interactions between users and corresponding items due to the graph structure of social data. Users might also be influenced by their social connections, which is the focus of social recommendation. Most works on recommendation systems try to obtain better representations of user embeddings and item embeddings. Compared with recommendation systems only focusing on interaction graphs, social recommendation has an additional task of combining user embedding from the social graph and interaction graph. This paper proposes a new method called SocialJGCF to address these problems, which applies Jacobi-Polynomial-Based Graph Collaborative Filtering (JGCF) to the propagation of the interaction graph and social graph, and a graph fusion is used to combine the user embeddings from the interaction graph and social graph. Experiments are conducted on two real-world datasets, epinions and LastFM. The result shows that SocialJGCF has great potential in social recommendation, especially for cold-start problems.

CitySEIRCast: an agent-based city digital twin for pandemic analysis and simulation

The COVID-19 pandemic has dramatically highlighted the importance of developing simulation systems for quickly characterizing and providing spatio-temporal forecasts of infection spread dynamics that take specific accounts of the population and spatial heterogeneities that govern pathogen transmission in real-world communities. Developing such computational systems must also overcome the cold-start problem related to the inevitable scarce early data and extant knowledge regarding a novel pathogen’s transmissibility and virulence, while addressing changing population behavior and policy options as a pandemic evolves. Here, we describe how we have coupled advances in the construction of digital or virtual models of real-world cities with an agile, modular, agent-based model of viral transmission and data from navigation and social media interactions, to overcome these challenges in order to provide a new simulation tool, CitySEIRCast, that can model viral spread at the sub-national level. Our data pipelines and workflows are designed purposefully to be flexible and scalable so that we can implement the system on hybrid cloud/cluster systems and be agile enough to address different population settings and indeed, diseases. Our simulation results demonstrate that CitySEIRCast can provide the timely high resolution spatio-temporal epidemic predictions required for supporting situational awareness of the state of a pandemic as well as for facilitating assessments of vulnerable sub-populations and locations and evaluations of the impacts of implemented interventions, inclusive of the effects of population behavioral response to fluctuations in case incidence. This work arose in response to requests from county agencies to support their work on COVID-19 monitoring, risk assessment, and planning, and using the described workflows, we were able to provide uninterrupted bi-weekly simulations to guide their efforts for over a year from late 2021 to 2023. We discuss future work that can significantly improve the scalability and real-time application of this digital city-based epidemic modelling system, such that validated predictions and forecasts of the paths that may followed by a contagion both over time and space can be used to anticipate the spread dynamics, risky groups and regions, and options for responding effectively to a complex epidemic.

An autoencoder-based recommendation framework toward cold start problem

An autoencoder-based recommendation framework toward cold start problem

LogOW: A semi-supervised log anomaly detection model in open-world setting

Log anomaly detection is a method for finding abnormal behavior and faults in systems. However, existing methods face two main challenges: the open-world problem and the cold-start problem. The open-world problem means that the test set may contain new classes that are not in the training set, while the cold-start problem means that the initial training data are scarce, both for normal and abnormal log sequences. Most existing methods assume a closed-world setting and rely on sufficient normal data, which limits their adaptability to new log environments.We propose LogOW, a novel log anomaly detection model that can learn from a few normal log sequences. The model finds emerging normal log sequences in the open-world setting through the open-world sample retrieval module. Through the incremental pre-training module, these log sequences are fine-tuned in an online mode for model parameters.First, we train a basic model from normal log sequences using Masked-Language Modeling(MLM). During the testing phase, we then combine the anomaly score and the uncertainty score obtained through a novel dynamic multi-mask to distinguish closed-world normal log sequences from the test set. Next, we cluster the open-world log sequences based on fused sequence and count features, and identify the abnormal ones and the new normal ones. Finally, we update our model with the new normal sequences in the next time period. Experiments on three log datasets and real-world airport logs show that our model outperforms traditional models in the open-world and lack of training data setting.

CsKT: Addressing cold-start problem in knowledge tracing via kernel bias and cone attention

csKT: Addressing cold-start problem in knowledge tracing via kernel bias and cone attention

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.

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

The expansion of e-commerce site platforms has brought about the need for personalized recommendation systems for the betterment of user experience and sales. In this paper, we propose a new approach for the recommendation system which is based on the dynamic behavior analysis of the users of the system. This involves analytics on the current data about customer activities such as buying history, browsing history, and likes to give recommendations that are up to date and very precise. Static models of the recommendation systems are contrasted to dynamic ones with the emphasis on the benefits of using for example collaborative filtering, content based filtering and other machine learning based hybrid systems to such systems. The performance metrics of accuracy, recall and F1 score confirm that the implementation of the system as proposed solves the cold start problem, enhances the scalability of the system and improves the accuracy of recommendations made. This work therefore opens the door to next generation recommendation engines which are more e-commerce oriented and can respond to the changing needs of customers more effectively.

Integrating Transformers into Recommendation Systems: A Hybrid Approach

In recent years, recommendation systems have become essential for various industries, from e-commerce to social media. This paper explores the integration of Transformer models within recommendation systems, which enhances the model's ability to capture long-range dependencies in user interactions. We present a hybrid recommendation approach combining collaborative filtering and Transformer-based content analysis. A case study is included, demonstrating how this integration handles both cold-start problems and typical user-item recommendation tasks.

A deep learning based hybrid recommendation model for internet users

Recommendation Systems (RS) play a crucial role in delivering personalized item suggestions, yet traditional methods often struggle with accuracy, scalability, efficiency, and cold-start challenges. This paper presents the HRS-IU-DL model, a novel hybrid recommendation system that advances the field by integrating multiple sophisticated techniques to enhance both accuracy and relevance. The proposed model uniquely combines user-based and item-based Collaborative Filtering (CF) to effectively analyze user-item interactions, Neural Collaborative Filtering (NCF) to capture complex non-linear relationships, and Recurrent Neural Networks (RNN) to identify sequential patterns in user behavior. Furthermore, it incorporates Content-Based Filtering (CBF) with Term Frequency-Inverse Document Frequency (TF-IDF) for in-depth analysis of item attributes. A key contribution of this work is the innovative fusion of CF, NCF, RNN, and CBF, which collectively address significant challenges such as data sparsity, the cold-start problem, and the increasing demand for personalized recommendations. Additionally, the model employs N-Sample techniques to recommend the top 10 similar items based on user-specified genres, leveraging methods like Cosine Similarity, Singular Value Decomposition (SVD), and TF-IDF. The HRS-IU-DL model is rigorously evaluated on the publicly available Movielens 100k dataset using train-test splits. Performance is assessed using metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Precision, and Recall. The results demonstrate that the HRS-IU-DL model not only outperforms state-of-the-art approaches but also achieves substantial improvements across these evaluation metrics, highlighting its contribution to the advancement of RS technology.

One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems

Sequential recommendation systems aim to predict users’ next likely interaction based on their history. However, these systems face data sparsity and cold-start problems. Utilizing data from other domains, known as multi-domain methods, is useful for alleviating these problems. However, traditional multi-domain methods rely on meaningless ID-based item representation, which makes it difficult to align items with similar meanings from different domains, yielding sup-optimal knowledge transfer. This paper introduces LLM-Rec , a framework that utilizes pre-trained large language models (LLMs) for domain-agnostic recommendation. Specifically, we mix user's behaviors from multiple domains and concatenate item titles into a sentence, then use LLMs for generating user and item representations. By mixing behaviors across different domains, we can exploit the knowledge encoded in LLMs to bridge the semantic across over multi-domain behaviors, thus obtaining semantically rich representations and improving performance in all domains. Furthermore, we explore the underlying reasons why LLMs are effective and investigate whether LLMs can understand the semantic correlations as the recommendation model, and if advanced techniques like scaling laws in NLP also work in recommendations. We conduct extensive experiments with LLMs ranging from 40M to 6.7B to answer the above questions and to verify the effectiveness of LLM-Rec in multi-domain recommendation \({}^{\ddagger}\) .

Deep Learning Based Music Recommendation Systems: A Review of Algorithms and Techniques

Abstract. This paper provides a thorough examination of the utilisation of deep learning in music recommendation systems, which have transformed consumer discovery and engagement with music on streaming platforms. Scalability challenges and the cold-start problem are among the constraints that conventional recommendation methods, such as content-based filtering and collaborative filtering, encounter, which hinder their ability to deliver personalised recommendations that are effective. The processing of multi-modal and sequential data is significantly improved by deep learning methodologies, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, and Autoencoders. This results in more precise and contextually pertinent music recommendations. Moreover, hybrid models that amalgamate deep learning with conventional techniques augment recommendation precision by synthesising user interaction data with acoustic characteristics. This paper examines essential performance metrics employed in the assessment of music recommendation systems, including precision, recall, F1-score, and Mean Reciprocal Rank (MRR). It also tackles issues including computational complexity, bias, and ethical dilemmas pertaining to data privacy.

Optimizing E-commerce Recommender Systems: A Comprehensive Review of Techniques and Future Directions

Abstract. This paper examines recommender systems in e-commerce by reviewing technologies and real-world applications and identifying the importance of big data analytics in recommender systems. In the study, three kinds of recommendation algorithms are discussed: collaborative filtering, content-based recommendation, and hybrid models. Collaborative filtering methods did well in the case of large-scale user data, but had cold-start and sparsity problems. Based on the content, recommended methods have strong personalized suggestion functions, but the information cocoon phenomenon is a risk, which decreases the contents diversity. Hybrid models are a combination approach between the two techniques, providing a flexible and robustness solution, but only a more complex computationally. This article also looks at the technology trends that have emerged lately, for example, the use of deep learning models, as well as the privacy-preserving techniques utilized in recommender systems. By analyzing and summarizing the existing research, this paper provides a reference basis for future optimization and application of recommender systems and points out potential research directions.

A collaborative filtering recommender systems: Survey

In the current digital landscape, both information consumers and producers encounter numerous challenges, underscoring the importance of recommender systems (RS) as a vital tool. Among various RS techniques, collaborative filtering (CF) has emerged as a highly effective method for suggesting products and services. However, traditional CF methods face significant obstacles in the era of big data, including issues related to data sparsity, accuracy, cold start problems, and high dimensionality. This paper offers a comprehensive survey of CF-based RS enhanced by machine learning (ML) and deep learning (DL) algorithms. It aims to serve as a valuable resource for both novice and experienced researchers in the field of RS. The survey is structured into two main sections: the first elucidates the fundamental concepts of RS, while the second delves into solutions for CF-based RS challenges, examining the specific tasks addressed by various studies, as well as the metrics and datasets employed.

Identify potential drug candidates within a high-quality compound search space.

The identification of potential effective drug candidates is a fundamental step in new drug discovery, with profound implications for pharmaceutical research and the healthcare sector. While many computational methods have been developed for such predictions and have yielded promising results, two challenges persist: (i) The cold start problem of new drugs, which increases the difficulty of prediction due to lack of historical data or prior knowledge. (ii) The vastness of the compound search space for potential drug candidates. In this study, we present a promising method that not only enhances the accuracy of identifying potential novel drug candidates but also refines the search space. Drawing inspiration from solutions to the cold start problem in recommender systems, we apply 'learning to rank' techniques to the field of new drug discovery. Furthermore, we propose using three similarity metrics to condense the compound search space into compact yet high-quality spaces, allowing for more efficient screening of potential drug candidates. Experimental results from two widely used datasets demonstrate that our method outperforms other state-of-the-art approaches in the new drug cold-start scenario. Additionally, we have verified that it is feasible to identify potential drug candidates within these high-quality compound search spaces. To our knowledge, this study is the first to address drug cold-start problem in such a confined space, potentially providing valuable insights and guidance for drug screening.