Recommendation Model Research Articles

E-commerce and Mobile Application Development in the Sports Industry

In order to achieve user recommendations that best match their current contextual needs, the author proposes a mobile service QoS (Quality of Service) hybrid recommendation model based on sports user situational awareness. Cluster the users and service items covered by mobile users based on their location contextual information according to the classification principle of autonomous systems, forming a collaborative filtering and recommendation mechanism for mobile user service items; In response to the cold start problem of new users and new projects in traditional QoS recommendation methods, prediction and recommendation of missing QoS attribute preference values are based on User based and Item based CF; In response to the problem of difficult determination of mixed recommendation weights caused by massive data and uneven distribution of service QoS attribute values in mobile network environments, MapReduce based ant colony neural network weight training is used for CF mixed recommendation. Experimental results have shown that the Hadoop sports industry has improved the operational efficiency of algorithms and reduced the time for global QoS preference prediction; And by comparing the operation results of the 10% and 100% sub datasets, it can also be seen that the acceleration ratio of the algorithm will continuously improve with the increase of data volume, thereby improving the operational efficiency of the recommendation algorithm. It has been proven that the MapReduce based ant colony neural network weight training method significantly reduces the global computation time of the algorithm and improves the operational efficiency of the recommendation system.

Maximizing the spread of information through content optimization

As data-driven prediction models advance, an increasing number of people are enjoying news personalized to their interests. The primary problem such recommendation models solve is to precisely match information with users and, in so doing, ensure that news spreads with greater efficiency. However, these techniques only help the media platform; they do not help those who produce the news. Hence, we devised a propagation framework based on a human-in-the-loop simulation that helps content authors maximize the spread of their messages through social networks. The framework works by acting on feedback provided by the simulation model. Additionally, the spread of information is formulated as a multi-objective optimization problem in which propagation is data-driven and simulated with machine learning techniques that leverage data on the historical behaviors of users. We additionally describe an implementation for this framework as an example of how the framework might be used in real life. On the practical side, the implementation uses text data from a blog to simulate the message's propagation, while, from a technical point of view, the multi-objective optimization problem is divided into an information retrieval problem and an integer programming problem, the results of which are fed back into the content editor as content operation strategies. A case study with the Sina Weibo microblog site not only validates the framework but also provides practitioners with insights into how to maximize the spread of information through social networking platforms. The results show that the proposed propagation framework is capable of increasing retweets by 7.9575 %. As an interesting aside, our experiments also show that the Weibo retweet lottery is both popular and a highly effective mechanism for increasing reposts.

Construction and preliminary application of large language model for reservoir performance analysis

A large language model (LLM) is constructed to address the sophisticated demands of data retrieval and analysis, detailed well profiling, computation of key technical indicators, and the solutions to complex problems in reservoir performance analysis (RPA). The LLM is constructed for RPA scenarios with incremental pre-training, fine-tuning, and functional subsystems coupling. Functional subsystem and efficient coupling methods are proposed based on named entity recognition (NER), tool invocation, and Text-to-SQL construction, all aimed at resolving pivotal challenges in developing the specific application of LLMs for RDA. This study conducted a detailed accuracy test on feature extraction models, tool classification models, data retrieval models and analysis recommendation models. The results indicate that these models have demonstrated good performance in various key aspects of reservoir dynamic analysis. The research takes some injection and production well groups in the PK3 Block of the Daqing Oilfield as an example for testing. Testing results show that our model has significant potential and practical value in assisting reservoir engineers with RDA. The research results provide a powerful support to the application of LLM in reservoir performance analysis.

Waste Governance and Empowerment: Evidence from Ponorogo, Indonesia

This research is a case study with a qualitative descriptive approach, aiming to describe and analyze Waste Governance on community empowerment in waste management in Ponorogo Regency, Indonesia. This research designs a recommendation model, taking into account empirical conditions in the field. Data collection in this study used interviews, observation, documentation, and focus group discussions. This research involved informants from various elements in Waste Governance, including government, community, industry, academics, mass media, NGOs/Communities, and regulators. This research stems from the low community empowerment in managing community-based waste management facilities in Ponorogo Regency, Indonesia. This condition is caused by the low participation and involvement of the community in various community empowerment programs in waste management, resulting in the community's role becoming less than optimal in Waste Governance. This study illustrates the weak aspects of Waste Governance in Ponorogo Regency, Indonesia, such as: weak collaboration between the community and academics in community empowerment in waste management, failure to accommodate waste governance in business, education, and environmental interests, and not maximizing the institutionalization of the waste management agenda through the Clean Friday Movement. This research recommends strengthening aspects of Waste Governance, namely encouraging local leadership as a driving force in waste governance. This aspect relates to the role of local leadership and community leaders in mobilizing various community-based waste management facilities. The results of this research are expected to contribute to developing Waste Governance theory, as well as provide practical benefits in the practice of Waste Governance in Indonesia.

Diversifying Collaborative Filtering via Graph Spreading Network and Selective Sampling.

Graph neural network (GNN) is a robust model for processing non-Euclidean data, such as graphs, by extracting structural information and learning high-level representations. GNN has achieved state-of-the-art recommendation performance on collaborative filtering (CF) for accuracy. Nevertheless, the diversity of the recommendations has not received good attention. Existing work using GNN for recommendation suffers from the accuracy-diversity dilemma, where slightly increases diversity while accuracy drops significantly. Furthermore, GNN-based recommendation models lack the flexibility to adapt to different scenarios' demands concerning the accuracy-diversity ratio of their recommendation lists. In this work, we endeavor to address the above problems from the perspective of aggregate diversity, which modifies the propagation rule and develops a new sampling strategy. We propose graph spreading network (GSN), a novel model that leverages only neighborhood aggregation for CF. Specifically, GSN learns user and item embeddings by propagating them over the graph structure, utilizing both diversity-oriented and accuracy-oriented aggregations. The final representations are obtained by taking the weighted sum of the embeddings learned at all layers. We also present a new sampling strategy that selects potentially accurate and diverse items as negative samples to assist model training. GSN effectively addresses the accuracy-diversity dilemma and achieves improved diversity while maintaining accuracy with the help of a selective sampler. Moreover, a hyper-parameter in GSN allows for adjustment of the accuracy-diversity ratio of recommendation lists to satisfy the diverse demands. Compared to the state-of-the-art model, GSN improved R @20 by 1.62%, N @20 by 0.67%, G @20 by 3.59%, and E @20 by 4.15% on average over three real-world datasets, verifying the effectiveness of our proposed model in diversifying overall collaborative recommendations.

Integrated Iot Approaches for Crop Recommendation and Yield-Prediction Using Machine-Learning

In this study, we present an integrated approach utilizing IoT data and machine learning models to enhance precision agriculture. We collected an extensive IoT secondary dataset from an online data repository, including environmental parameters such as temperature, humidity, and soil nutrient levels, from various sensors deployed in agricultural fields. This dataset, consisting of over 1 million data points, provided comprehensive insights into the environmental conditions affecting crop yield. The data were preprocessed and used to develop predictive models for crop yield and recommendations. Our evaluation shows that the LightGBM, Decision Tree, and Random Forest classifiers achieved high accuracy scores of 98.90%, 98.48%, and 99.31%, respectively. The IoT data collection enabled real-time monitoring and accurate data input, significantly improving the models’ performance. These findings demonstrate the potential of combining IoT and machine learning to optimize resource use and improve crop management in smart farming. Future work will focus on expanding the dataset to include more diverse environmental factors and exploring the integration of advanced deep learning techniques for even more accurate predictions.

Enhancing Book Recommendation Accuracy through User Rating Analysis and Collaborative Filtering Techniques

Since online electronic books have become popular, book recommendation systems have been invented and challenged to handle the high demand from users in the digital era. This study aimed to develop and evaluate a book recommendation model using data mining techniques through RapidMiner Studio. The datasets used were comprised of 981,756 user ratings. Before conducting the data analytics, the data was pre-processed to eliminate duplicates and retain only the highest ratings. Collaborative Filtering (CF) techniques, particularly k-Nearest Neighbours (k-NN) and Matrix Factorization (KF), were employed to elicit insightful information for development and to highlight their capabilities in handling enormous datasets. Furthermore, statistical analysis, visualization, elementary modelling, and model combinations were investigated to compare their performance. To reinforce creditability, modelling techniques and parameter adjustments were integrated to optimize the performance of the algorithms, since the results indicated that different model settings and data partitions impacted the effectiveness of the recommendation system. Additionally, these results demonstrated the potential of hybrid models in improving the accuracy and efficiency of recommendation systems and highlighted the trade-off between algorithmic approaches and dataset characteristics that interplay in optimizing the performance of recommendation systems.

A Study on Doctor Recommendation Model in Medical Guidance Services

In medical guidance services, it is of great significance to match the appropriate department and doctor by digging deeper into patients’ demands. However, accurate matching of doctors requires the ability to locate the exact department based on the text of the patients’ chief complaint, and then select the matching doctor by considering the patients’ condition, the doctor’s professionalism, and the patients’ preference. To this end, this paper proposes a department classification model on the basis of Convolutional Neural Networks (CNN) as well as Robustly optimized BERT approach (RoBERTa) with an attention mechanism. The model firstly extracts the patients’ chief complaint texts features by convolution layer, and then introduces the attention mechanism to assign different weights to different features. Subsequently, these features are fused with the features extracted by RoBERTa for classification. In addition, this paper proposes a doctor recommendation algorithm that considers both patient similarity and patient preference. Through the in-depth analysis on the patients’ condition claims, various weights are assigned to various influencing factors, and then the matching degree is calculated to achieve the accurate recommendation of doctors. The experimental results reveal that the proposed department classification model’s accuracy on the dataset is 93.4%, and the Normalized Discounted Cumulative Gain (NDCG) of the doctor recommended algorithm is 90.7%. In this way, the proposed model effectively improves patient-doctoral matching with excellent performance.

A service-recommendation method for the Internet of Things leveraging implicit social relationships

Integrating social-relationship information is widely considered an effective means to addressing the sparsity issue in Internet-of-Things (IoT) service recommendations. However, owing to platform variations and privacy concerns, acquiring explicit social-relationship information has become challenging. Therefore, researchers are gradually focusing on leveraging implicit social-relationship information to enhance recommendation effectiveness. Nevertheless, when using implicit social relationships, both user/service-implicit social-relationship and user-service interaction information rely on the same rating matrix, leading to nonindependence and coupling, which influence the recommendation model. To address this challenge, the present paper introduces a unique approach for IoT service recommendations, leveraging implicit social-relationship information (short for ISoc-IoTRec). First, we construct a user-service interaction graph, user-implicit social-relationship graph, and service-implicit social-relationship graph, learning their node embeddings through graph neural networks (GNNs). Subsequently, we introduce a cross information control module to achieve feature separation, ensuring that the user and service embeddings learned from different graphs remain independent in representation, thereby alleviating the nonindependence and coupling issues arising from the same data source. Following feature separation, the user and service embeddings are aggregated separately. Through an attention mechanism module, the model can selectively emphasize or attenuate the impact of each feature while considering the overall information, further addressing nonindependence and coupling issues. Extensive experiments conducted on three real-world datasets underscore the remarkable performance of ISoc-IoTRec, significantly outperforming existing recommendation algorithms.

Enhancing Recommendation Diversity and Novelty with Bi-LSTM and Mean Shift Clustering

In the digital age, personalized recommendation systems have become crucial for information dissemination and user experience. While traditional systems focus on accuracy, they often overlook diversity, novelty, and serendipity. This study introduces an innovative recommendation system model, Time-based Outlier Aware Recommender (TOAR), designed to address the challenges of content homogenization and information bubbles in personalized recommendations. TOAR integrates Neural Matrix Factorization (NeuMF), Bidirectional Long Short-Term Memory Networks (Bi-LSTM), and Mean Shift clustering to enhance recommendation accuracy, novelty, and diversity. The model analyzes temporal dynamics of user behavior and facilitates cross-domain knowledge exchange through feature sharing and transfer learning mechanisms. By incorporating an attention mechanism and unsupervised clustering, TOAR effectively captures important time-series information and ensures recommendation diversity. Experimental results on a news recommendation dataset demonstrate TOAR’s superior performance across multiple metrics, including AUC, precision, NDCG, and novelty, compared to traditional and deep learning-based recommendation models. This research provides a foundation for developing more intelligent and personalized recommendation services that balance accuracy with content diversity.

Hypergraph contrastive learning for recommendation with side information

PurposeThis paper addresses the limitations of current graph neural network-based recommendation systems, which often neglect the integration of side information and the modeling of complex high-order interactions among nodes. The research motivation stems from the need to enhance recommendation performance by effectively utilizing all available data. We propose a novel method called MSHCN, which leverages hypergraph neural networks to integrate side information and model complex interactions, thereby improving user and item representations.Design/methodology/approachThe MSHCN method employs a hypergraph structure to incorporate various types of side information, including social relationships among users and item attributes, which are essential for enriching user and item representations. The k-means clustering algorithm is utilized to create item-associated hypergraphs, while sentiment analysis on user reviews refines the modeling of user interests. Additionally, hypergraphs are constructed for user-user and item-item interactions based on interaction similarity. MSHCN also incorporates contrastive learning as an auxiliary task to enhance the representation learning process.FindingsExtensive experiments demonstrate that MSHCN significantly outperforms existing recommendation models, particularly in its ability to capture and utilize side information and high-order interactions. This results in superior user and item representations and improved recommendation performance.Originality/valueThe novelty of MSHCN lies in its use of a hypergraph structure to integrate diverse side information and model intricate high-order interactions. The incorporation of contrastive learning as an auxiliary task sets it apart from other hypergraph-based models, providing a significant enhancement in recommendation accuracy.

The Dilemma of Identifying Copyright Infringement Liability of Network Platform under Algorithm Recommendation Model

In the digital age, the application of algorithm technology realizes the efficient transformation from “people looking for information” to “information looking for people”, which greatly expands the transmission boundary of articles and video content. However, to some extent, this kind of change also intensifies the problem of copyright infringement on the network platform. Once online copyright works are published, they can be widely disseminated, and it is difficult to remedy the damage suffered by them. The existing laws and regulations have deficiencies in this regulation. This paper starts from the dilemma of network copyright protection under the algorithm recommendation mode, and puts forward some relief measures such as platform filtering obligation based on the actual situation.

Denoising Alignment with Large Language Model for Recommendation

The mainstream approach of GNN-based recommendation aggregates high-order ID information associated with the node in the user-item graph. The aggregation pattern using ID as signal has two disadvantages: lack of textual semantics and the impact of interaction noise. These disadvantages pose a threat to effectively learn user preferences, especially in capturing intricate user-item semantic relationships. Although large language models (LLMs) allow the integration of rich textual information into recommenders and have had groundbreaking applications in recommender systems, current works need to bridge the gap between different representation spaces. This is because LLMs-based methods align the representations of GNN-based models only by using text embedding of LLM, leading to unsatisfactory results. To address this challenge, we propose a D enoising A lignment framework with L LMs for GNN-based R ecommenders (DALR), which aims to align structural representation with textual representation and mitigate the effects of noise. Specifically, We propose a modeling framework that integrates the representation of graph structure with textual information from LLMs to capture intricate user-item interactions. We also suggest an alignment paradigm to enhance representation performance by aligning semantic signals from LLMs and structural features from GNN models. Additionally, we introduce a contrastive learning scheme to relieve the impact of noise and improve model performance. Extensive experiments on public datasets demonstrate that our model consistently outperforms the state-of-the-art methods. DALR achieves improvements ranging from 2.82% to 12.20% in Recall@5 and from 1.04% to 3.48% in NDCG@5 compared to the strongest baseline model, using the Steam dataset as an example.

Research on recommended model of personalized interior environment

Personalized recommendation systems are a common feature of e-commerce, streaming services, and other fields. However, they are not common in the field of interior environment design. Existing international research tends to prioritize deep learning-based recommendation algorithms. These methods rely heavily on large-scale data and complex models to improve the accuracy of recommendations. However, they often face significant limitations. Therefore, this paper proposes a personalized recommendation model for interior environment design based on clustering collaborative filtering algorithm and user portrait. The model improves the traditional collaborative filtering recommendation algorithm. Based on the established UPICF recommendation algorithm, the constructed model is verified through performance analysis and practical application test. The experimental results show that when the number of neighbors is 20, the MAE of the model is 0.7035, which has better personalized recommendation performance. In addition, in the personalized recommendation application of interior environment design, the click-through rate of the model is increased by 0.115, and the purchase conversion rate of users is increased by about 0.270, which further proves the effectiveness of the model. The results show that this model can provide more accurate, diversified and personalized indoor environment design solutions to meet the individual needs of users.

DrugDoctor: enhancing drug recommendation in cold-start scenario via visit-level representation learning and training.

Medication recommendation is a crucial application of artificial intelligence in healthcare. Current methodologies mostly depend on patient-level longitudinal representation, which utilizes the entirety of historical electronic health records for making predictions. However, they tend to overlook a few key elements: (1) The need to analyze the impact of past medications on previous conditions. (2) Similarity in patient visits is more common than similarity in the complete medical histories of patients. (3) It is difficult to accurately represent patient-level longitudinal data due to the varying numbers of visits. To our knowledge, current models face difficulties in dealing with initial patient visits (i.e. in cold-start scenarios) which are common in clinical practice. This paper introduces DrugDoctor, an innovative drug recommendation model crafted to emulate the decision-making mechanics of human doctors. Unlike previous methods, DrugDoctor explores the visit-level relationship between prescriptions and diseases while considering the impact of past prescriptions on the patient's condition to provide more accurate recommendations. We design a plug-and-play block to effectively capture drug substructure-aware disease information and effectiveness-aware medication information, employing cross-attention and multi-head self-attention mechanisms. Furthermore, DrugDoctor adopts a fundamentally new visit-level training strategy, aligning more closely with the practices of doctors. Extensive experiments conducted on the MIMIC-III and MIMIC-IV datasets demonstrate that DrugDoctor outperforms 10 other state-of-the-art methods in terms of Jaccard, F1-score, and PRAUC. Moreover, DrugDoctor exhibits strong robustness in handling patients with varying numbers of visits and effectively tackles "cold-start" issues in medication combination recommendations.

A two-stage recommendation optimization algorithm based on item popularity and user features

Financial product recommendation algorithms are mainly product-centered. This article proposes a two-stage recommendation optimization algorithm based on item popularity and user features, named CPCF-TSP, that can make full use of the demographic characteristics of users and mitigate the problem of users being more inclined to choose “hot” financial products. A popularity weight factor is introduced to normalize popularity and modify Pearson's similarity function. The modified Pearson's similarity function is combined with popularity normalization and user features to improve modeling performance. The two-stage recommendation optimization procedure was combined with a collaborative filtering algorithm to improve recommendation precision. CPCF-TSP fully considers user features in building a hybrid recommendation model and solves the problem of user cold-start. It can also mitigate popularity deviations and improve recommendation precision. MovieLens data and Santander Bank client trading data were used in a case study. The results show that the algorithm reduces inaccuracy in the calculation of the weights for recommendation popularity and similarity and is especially suitable for recommending financial products in which user information can be easily collected and the number of users is far greater than the number of products considered.

Pairwise Intent Graph Embedding Learning for Context-Aware Recommendation with Knowledge Graph

Different from the data sparsity that traditional recommendations suffer from, context-aware recommender systems (CARS) face specific sparsity challenges related to contextual features, i.e., feature sparsity and interaction sparsity. How knowledge graphs address these challenges remains under-discussed. To bridge this gap, in this paper, we first propose a novel pairwise intent graph (PIG) containing nodes of users, items, entities, and enhanced intents to integrate knowledge graphs into CARS efficiently. Enhanced intent nodes are generated through the specific fusion of relational sub-intent and contextual sub-intent, and they are derived from semantic information and contextual information, respectively. We develop a pairwise intent graph embedding learning (PING) framework based on it. Specifically, our PING uses a pairwise intent joint graph convolution module to obtain refined embedding of all the features, where each enhanced intent node acts as a hub to effectively propagate information among different features and between all the features and knowledge graphs. Then, a recommendation module with refined embeddings is used to replace the randomly initialized embeddings of downstream recommendation models to improve model performance. Extensive experiments on three public datasets and some real-world scenarios verify the effectiveness and compatibility of our PING.

Contrastive Learning-Based Personalized Tag Recommendation.

Personalized tag recommendation algorithms generate personalized tag lists for users by learning the tagging preferences of users. Traditional personalized tag recommendation systems are limited by the problem of data sparsity, making the personalized tag recommendation models unable to accurately learn the embeddings of users, items, and tags. To address this issue, we propose a contrastive learning-based personalized tag recommendation algorithm, namely CLPTR. Specifically, CLPTR generates augmented views of user-tag and item-tag interaction graphs by injecting noises into implicit feature representations rather than dropping nodes and edges. Hence, CLPTR is able to greatly preserve the underlying semantics of the original user-tag or the item-tag interaction graphs and avoid destroying their structural information. In addition, we integrate the contrastive learning module into a graph neural network-based personalized tag recommendation model, which enables the model to extract self-supervised signals from user-tag and item-tag interaction graphs. We conduct extensive experiments on real-world datasets, and the experimental results demonstrate the state-of-the-art performance of our proposed CLPTR compared with traditional personalized tag recommendation models.

Child life specialists predict successful MRI scanning in unsedated children 4 to 12years old.

It can be challenging for children to cooperate for a magnetic resonance imaging (MRI) exam. General anesthesia is often used to ensure a high-quality image. When determining the need for general anesthesia, many institutions use a simple age cutoff. Decisions on the necessity for anesthesia are often left to schedulers who lack training on determination of patient compliance. The study aimed to evaluate whether screening questions administered by certified child life specialists (CCLS) could successfully predict which children could complete an MRI without sedation. This is a retrospective, institutional review board approved study. Data was collected as part of a quality improvement program, where a CCLS screened 4- to 12-year-old children scheduled for MRI scanning using a questionnaire. Parent responses to the screening questions, CCLS's recommendation for scheduling the MRI awake, start and end time for the MRI scan, and scan success were recorded. A predictive model for the CCLS's recommendation was developed using the child's age, estimated scan length, scan difficulty, and the parent's responses to the screening questions. The primary outcome measure was a successfully completed MRI not requiring additional imaging under anesthesia. Of the 403 screened children, 317 (79%) were recommended to attempt the MRI without anesthesia. The median age of participants was 7 (IQR 4-17) years. Overall, 309 of 317 (97.5%) participants, recommended by the CCLS for the program, met the primary outcome of successful MRI completion on their first attempt. The multivariable regression model which included clinical information about the child's age, estimated scan length, scan difficulty, and four of the six parent screening questions had excellent performance (area under the curve = 0.89). Information collected by the CCLS via screening along with the child's age, the estimated scan length, and difficulty can help predict which children are likely to successfully complete a non-sedate MRI.

GIIE: A Graph-based News Recommendation Model with Intrinsic Interest Enhancement

News recommendation aims to offer potentially interesting news items to a specific user, guided by his historical browsing behaviors. Existing methods failed to effectively address the knowledge sparsity issue that the user may have sparse behaviors and the news may own sparse features. To address the problem, we propose a graph-based news recommendation model with intrinsic interest enhancement, named GIIE , leveraging intrinsic interests and neighbor information to enhance the representation of sparse users and news. Concretely, to fully take advantage of the intrinsic interests, we design an interest encoder based on an interest-type graph with a learnable structure, and explore the interest embeddings from news types. Then we inject the obtained interest embeddings into news, and represent the user by aggregating the clicked news under the same interest and across different interests sequentially. These interests can build a bridge between users, so that users with sparse behaviors can implicitly share knowledge with other users, thereby enhancing their representation. To properly introduce the neighbor knowledge, we propose a graph-based neighbor enhancing mechanism. First, we design a news relation graph and a user relation graph in encoders. Then based on these graphs, we take the attention module to aggregate additional knowledge from neighbors, enhancing sparse news and user representations. To avoid feature ambiguity, we adopt a way to represent the current item (user and news) and its neighbors separately, and then do adaptive aggregation. We evaluate GIIE on the public news recommendation dataset MIND-Large and MIND-Small. Experimental results show that our model can solve the knowledge sparse problem, and outperforms current state-of-the-art models in four indicators.