Recommendation Accuracy Research Articles

Spatial extension of soil water regime variables derived from soil moisture values using geomorphological variables in Hungary

Accurate measurement and spatial extension of soil properties are essential in geoinformatics and precision agriculture for effective resource management, particularly irrigation planning. This study addresses the challenge of extending soil moisture data and related soil water regime variables in heterogeneous agricultural landscapes by integrating geomorphological variables (GVs) derived from high-resolution digital elevation models (DEM). In digital soil mapping, machine learning and geostatistical models often struggle with validation due to data scarcity and variability across space through many geographical regions that come from the point readings of soil properties. A different approach was developed in the form of a new methodology combining two hourly Sentek soil moisture measurements from the topsoil with DEM-derived GVs to model and extend soil water regime variables. The research was conducted on an agricultural field in a hilly area with diverse geomorphological variability. The model’s performance was validated using cross-validation techniques. The monitoring and spatial extension results indicate that GVs enhance the spatial prediction of soil moisture, capturing periodic fluctuations in the upper soil layer more effectively by using in-situ, time series soil moisture sensor readings rather than traditional, on field, one time reading approaches. We observed that certain GVs, such as the slope, both type of curvatures and the convergence, were strong predictors of soil moisture variation, enabling the model to produce more accurate irrigation recommendations for agricultural areas with similar geomorphological areas. One of the soil water regime variables was validated during the preliminary validation with mixed results. The main issue was coming from the field use and spatial scarcity of the measurements. Our approach not only provides a different method for spatially extending the current soil water regime data but also offers a framework for improving irrigation decision-making with the help of other value rates and limit related soil regime variables derived from the time series readings from the soil moisture sensors. With its variables, the model allows for forecasts of soil moisture changes, which can inform better irrigation scheduling and water resource management, all based on data from the soil monitoring sensor system.

Temporal dual-target cross-domain recommendation framework for next basket recommendation

Next Basket Recommender systems in e-commerce face challenges such as data sparsity, evolving user preferences, and cross-domain transfer limitations. We propose the Temporal Dual-Target Cross-Domain Recommendation Framework (T-DualCRF) to address these issues. T-DualCRF integrates multi-channel embeddings (user feedback, knowledge graphs, temporal features) and a dual-target mechanism for robust cross-domain knowledge transfer. It also employs time-aware embeddings and a temporal heterogeneous graph to model user preference changes. The framework’s hybrid optimization mechanism, combining the Multi-Verse Optimizer and Whale Optimization Algorithm, enhances recommendation accuracy and stability. Experimental results on Amazon datasets show that T-DualCRF significantly outperforms existing models, with improvements of up to 20% in F1-score and 17% in NDCG, effectively mitigating data sparsity and adapting to real-time user behavior changes.

Edge‐Optimized Neural Networks for Real‐Time English Corpus Recommendation

ABSTRACTThis paper presents a lightweight framework for real‐time English corpus recommendation optimized for edge computing environments. Traditional recommendation systems, though effective in modeling complex user‐content interactions, often suffer from excessive computational demands, making them unsuitable for deployment on resource‐constrained edge devices. To tackle these limitations, we introduce a novel solution that efficiently balances advanced interaction modeling with computational cost optimization. The framework integrates a robust baseline model that captures rich user‐content interactions while employing knowledge distillation techniques to transfer critical information, ensuring that high‐quality recommendations are maintained even with reduced computational overhead. Our approach leverages real‐time adaptability to edge environments, providing both speed and accuracy. Experimental evaluations on benchmark datasets reveal significant reductions in response time, without compromising the accuracy of recommendations, thus making it ideal for real‐time applications in edge computing scenarios.

Crowd-CapsNet: capsule network based adaptive crowdsourcing task recommendation

Purpose The crowdsourcing software development platforms organize geographically distributed developers to complete various developing tasks, bringing convenience and efficiency to users. However, with the increasing number of both developers and tasks, it becomes more and more challenging to match tasks and suitable developers, especially for imbalanced data. The purpose of this paper is to propose an accurate and diverse recommendation model for crowdsourcing tasks. Design/methodology/approach A revised circle loss function is applied to achieve a certain adaptive ability, which is critical for imbalanced data, it guarantees diversity by maximizing the target label score and leveraging mathematical approximation to automatically balance the weights. Besides, the authors leverage the capsule network to obtain the semantic feature of tasks’ descriptions, modify the dynamic routing mechanism to better learn users’ preferences and improve the recommendation accuracy. Findings The comprehensive experiments conducted on real crowdsourcing platform data demonstrate that the proposed Crowd-CapsNet model can achieve high recommendation accuracy with a certain diversity. It improves around 1% accuracy with only 37% training time of the LSFA approach. Originality/value This paper proposes Crowd-CapsNet, an adaptive crowdsourcing task recommendation model. A relatively general feature pre-processing method describes crowd-sourcing tasks and the modified capsule network further obtains the semantic features to improve the recommendation accuracy and diversity.

Recommendation System for Selecting Electronic Products Using Content-Based Filtering Method

This study aims to develop a recommendation system for electronic products using the Content-Based Filtering method. In this research, calculations were performed to identify 12 products that exhibit similarity based on their respective categories. The method employed for these calculations was cosine similarity, which measures the degree of similarity between products. The analysis results indicate that there are three products with the highest similarity values, specifically 73, 71.15, and 64.89. These products were selected based on their relevant characteristic similarities and features, thereby providing accurate recommendations for consumers. This recommendation system is expected to significantly enhance the online shopping experience by assisting consumers in finding products that align closely with their preferences and needs. Consequently, this research offers substantial contributions to companies seeking to improve customer satisfaction and operational efficiency, ultimately leading to better consumer engagement and increased sales in the competitive electronic market.

Modelling Concept Drift in Dynamic Data Streams for Recommender Systems

Recommendation systems play a crucial role in modern e-commerce and streaming services. However, the limited availability of public datasets hampers the rapid development of more efficient and accurate recommendation algorithms within the research community. This work introduces a stream-based data generator designed to generate user preferences for a set of items while accommodating progressive changes in user preferences. The underlying principle involves using user/item embeddings to derive preferences by exploring the proximity of these embeddings. Whether randomly generated or learned from a real finite data stream, these embeddings serve as the basis for generating new preferences. We investigate how this fundamental model can adapt to shifts in user behavior over time; in our framework, changes correspond to alterations in the structure of the tripartite graph, reflecting modifications in the underlying embeddings. Through an analysis of real-life data streams, we demonstrate that the proposed model is effective in capturing actual preferences and the changes that they can exhibit over time. Thus, we characterize these changes and develop a generalized method capable of simulating realistic data, thereby generating streams with similar yet controllable drift dynamics.

Analyzing and Designing Decision Support Systems for Stroke Patient Daily Treatment

Stroke is one of the neurological diseases that often requires complex management and treatment. Making the right decisions in diagnosing and treating stroke patients can have a significant impact on the recovery process and the quality of life for patients. To assist healthcare professionals and patients in making more informed decisions, this research has developed the "StrokeCare Navigator," a web-based Decision Support System (DSS) that utilizes the Decision Tree C4.5 algorithm. This system allows users, including healthcare professionals and patients, to input symptoms and patient medical information, providing an initial diagnosis of the type and severity of the stroke. Additionally, the system offers personalized treatment guidelines, treatment recommendations, and online patient monitoring services. The Decision Tree C4.5 model used in this system was developed through training with relevant patient data. Evaluation results indicate that the system can provide accurate and beneficial recommendations for healthcare professionals and patients. Testing and patient monitoring in clinical practice also demonstrate the potential to enhance stroke patient care. Therefore, StrokeCare Navigator is expected to be a valuable tool in stroke patient management and treatment, ultimately improving the prospects of patient recovery and providing better guidance for healthcare professionals. This research also provides deeper insights into the implementation of the Decision Tree C4.5 algorithm in the context of Decision Support Systems (DSS) in the medical field.

Variational Autoencoders-Based Algorithm for Multi-Criteria Recommendation Systems

In recent years, recommender systems have become a crucial tool, assisting users in discovering and engaging with valuable information and services. Multi-criteria recommender systems have demonstrated significant value in assisting users to identify the most relevant items by considering various aspects of user experiences. Deep learning (DL) models demonstrated outstanding performance across different domains: computer vision, natural language processing, image analysis, pattern recognition, and recommender systems. In this study, we introduce a deep learning model using VAE to improve multi-criteria recommendation systems. Specifically, we propose a variational autoencoder-based model for multi-criteria recommendation systems (VAE-MCRS). The VAE-MCRS model is sequentially trained across multiple criteria to uncover patterns that allow for better representation of user–item interactions. The VAE-MCRS model utilizes the latent features generated by the VAE in conjunction with user–item interactions to enhance recommendation accuracy and predict ratings for unrated items. Experiments carried out using the Yahoo! Movies multi-criteria dataset demonstrate that the proposed model surpasses other state-of-the-art recommendation algorithms, achieving a Mean Absolute Error (MAE) of 0.6038 and a Root Mean Squared Error (RMSE) of 0.7085, demonstrating its superior performance in providing more precise recommendations for multi-criteria recommendation tasks.

Privacy-Preserving Sequential Recommendation with Collaborative Confusion

Sequential recommendation has attracted a lot of attention from both academia and industry, however the privacy risks associated with gathering and transferring users’ personal interaction data are often underestimated or ignored. Existing privacy-preserving studies are mainly applied to traditional collaborative filtering or matrix factorization rather than sequential recommendation. Moreover, these studies are mostly based on differential privacy or federated learning, which often lead to significant performance degradation, or have high requirements for communication. In this work, we address privacy-preserving from a different perspective. Unlike existing research, we capture collaborative signals of neighbor interaction sequences and directly inject indistinguishable items into the target sequence before the recommendation process begins, thereby increasing the perplexity of the target sequence. Even if the target interaction sequence is obtained by attackers, it is difficult to discern which ones are the actual user interaction records. To achieve this goal, we introduce a novel sequential recommender system called CLOUD ( C o L laborative-c O nfusion seq U ential recommen D er), which incorporates a collaborative confusion mechanism to modify the raw interaction sequences before conducting recommendation. Specifically, CLOUD first calculates the similarity between the target interaction sequence and other neighbor sequences to find similar sequences. Then, CLOUD considers the shared representation of the target sequence and similar sequences to determine the operation to be performed: keep, delete, or insert. A copy mechanism is designed to make items from similar sequences have a higher probability to be inserted into the target sequence. Finally, the modified sequence is used to train the recommender and predict the next item. We conduct extensive experiments on three benchmark datasets. The experimental results show that CLOUD achieves a maximum modification rate of 66.57% on interaction sequences, and obtains over 99% recommendation accuracy compared to the state-of-the-art sequential recommendation methods. This proves that CLOUD can effectively protect user privacy at minimal recommendation performance cost, which provides a new solution for privacy-preserving for sequential recommendation. Our implementation is available at https://github.com/weiwang0927/CLOUD .

Enhancing Security in CNN-Based Travel Recommendation Models Using CKKS Homomorphic Encryption

This study explores the integration of CKKS homomorphic encryption with convolutional neural networks (CNNs) to enhance the security of travel recommendation systems. By adapting CNN architectures to operate efficiently on encrypted data using CKKS, we address the challenge of maintaining the users’ privacy without compromising system performance. Key results indicate significant improvements in data security with minimal impact on recommendation accuracy.

Optimizing Personalized and Context-Aware Recommendations in Pervasive Computing Environments

The researchers in the current era provided many new recommendation methodologies. Though various recommendation techniques exist, there is a need to develop a unique technique for capturing latent factors and patterns from sparse and high-dimensional data in pervasive environments, specifically for optimizing dynamic recommendations. This study proposes a hybrid approach for optimizing dynamic recommendations in pervasive environments by combining Non-Negative Matrix Factorization (NMF) with deep learning and reinforcement learning techniques. The goal is to overcome the challenge of capturing latent factors and patterns from sparse and high-dimensional data. By leveraging NMF, meaningful latent factors are extracted, while deep learning, specifically Faster recurrent neural networks (FRNNs), learns complex feature representations. Reinforcement learning algorithms optimize the recommendation policy based on user feedback. This Hybrid Context-Aware Optimized Recommendation (HCOR) approach improves recommendation accuracy and relevance in pervasive environments, adapts to changing contexts, and enhances user experiences. The performance benefits are achieved by effectively capturing latent factors and patterns, resulting in improved accuracy and the ability to provide personalized and context-aware recommendations. The performance indicators to validate the research work include the recommendations' accuracy, relevance, and adaptability in pervasive environments. Additionally, metrics, such as precision, recall, and F1-score, are used to evaluate the effectiveness of the hybrid approach in capturing latent factors and patterns. User feedback and satisfaction are also measured to assess the impact on user experiences. The HCOR approach shows substantial performance gains, measuring a precision of 0.932, a recall of 0.922, and an F1-score of 0.943, which indicates the excellent ability of the approach to deliver accurate and personalized recommendations in a pervasive environment.

Dynamic long short-term memory model for enhanced product recommendations in e-commerce

Recommendation systems are pivotal for personalized user experiences, employing algorithms to predict and suggest items aligned with user preferences. Deep learning (DL) models, such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), excel in capturing sequential dependencies, enhancing recommendation accuracy. However, challenges persist in session-based recommendation systems, particularly with gradient descent and class imbalances. Addressing these challenges, this work introduces dynamic LSTM (D-LSTM), a novel DL-based recommendation system tailored for dynamic E-commerce environments. The primary objective is to optimize recommendation accuracy by effectively capturing temporal dependencies within user sessions. The methodology involves the integration of D-LSTM with weight matrix optimization and a Bayesian personalized ranking (BPR) adaptable learning rate optimizer to enhance learning efficiency. Experimental results demonstrate the efficacy of D-LSTM, showing significant improvements over existing models. Specifically, comparisons with the hybrid time-centric prediction (HTCP) model reveal a performance enhancement of 19.4%, 17.2%, 35.41%, and 21.99% for hit-rate (HR) and mean reciprocal rank (MRR) in 10k and 20k recommendation sets using the Tmall dataset. These findings underscore the superior performance of D-LSTM, highlighting its potential to advance personalized recommendations in dynamic E-commerce settings.

ConvSeq-MF: Convo-Sequential Matrix Factorization for recommender system

In the domain of recommendation, the fusion of user historical preferences and item features has emerged as a promising field to enhance recommendation accuracy and mitigate the sparsity problem. This research presents a novel approach to recommendation systems by integrating both user and item content auxilary information. By harnessing the rich contextual data associated with users and items, our hybrid aproach ConvSeq-MF endeavors to provide more personalized and accurate recommendations. As the name indivates, it is based on a matrix factorization approach driven by joint venture of semantic and contextual information of both user’s and item’s. Series of experimentation on three real-world datasets shows the suggested methodology’s practicality and efficacy over otther baselines. To the best of our knowledge, the data demonstrate that the suggested model works better than other state of the art frameworks.

Granular intents learning via mutual information maximization for knowledge-aware recommendation

Knowledge-aware recommender systems, which utilize knowledge graphs (KGs) to enrich item information, have been shown to improve the accuracy and explainability of recommendations. Besides, KGs are further explored to determine the intent of choosing items (i.e., the reason why users select items of interest). Conventional methods represent intents either as sets of relations in a KG or as KG entities. However, such approaches fail to fully leverage the combined information provided by both entities and relations. To address this issue, we propose a new KG-based user Intent Extraction Framework (KIEF) to capture user intents at a more fine-grained level for recommendation. Specifically, we propose a novel intent representation constructed with relation-aware entity representation, encouraging finer granularity for user intents. Furthermore, since a KG may contain noisy information that impairs the quality of user intent, it is compulsory to consider which factors in a KG are important to represent a user’s intent. Thus, we introduce global intent which are comprehensive features for the entire interactions of all users and local intent, which are empirical features of individual users from personal history. By maximizing mutual information between global and local intents, KIEF captures user preference for items. Through extensive experiments on four real-world benchmark datasets, we prove the superior performance of KIEF over the state-of-the-art and analyze interpretable explanations for understanding user intents.

A multi-criteria trust-enhanced collaborative filtering algorithm for personalized tourism recommendations

The exponential growth of online information has LED to significant challenges in navigating data overload, particularly in the tourism industry. Travelers are overwhelmed with choices regarding destinations, accommodations, dining, and attractions, making it difficult to select options that best meet their needs. Recommender systems have emerged as a promising solution to this problem, aiding users in decision-making by providing personalized suggestions based on their preferences. Traditional collaborative filtering (CF) methods, however, face limitations, such as data sparsity and reliance on single rating scores, which do not fully capture the complexity of user preferences. This study proposes a hybrid multi-criteria trust-enhanced CF (HMCTeCF) algorithm to improve the accuracy and robustness of tourism recommendations. HMCTeCF improves the quality of recommendations by integrating multi-criteria user preferences with trust relationships among users and between items. Experimental results using real-world datasets, including Restaurants-TripAdvisor and Hotels-TripAdvisor, demonstrate that HMCTeCF outperforms benchmark CF-based recommendation methods. It achieves higher prediction accuracy and coverage rate, effectively addressing the data sparsity problem. This innovative algorithm facilitates a more personalized and enriching travel experience, particularly in scenarios with limited user data. The findings highlight the importance of considering multiple criteria and trust relationships in developing robust recommendation systems for the tourism industry.

Hesitant fuzzy clustering with convolutional spiking neural network for movie recommendations

The movie recommender system is one of the most influential and practical tools for aiding individuals in quickly selecting films to watch. Despite numerous academic efforts to employ recommender systems for various purposes, such as movie-watching and book-buying, many studies have overlooked user-specific movie recommendations. This paper introduces a novel approach for movie recommendations that combines the hesitant fuzzy clustering with a convolutional spiking neural network movie recommender system. The initial step involves acquiring input data from benchmark datasets like MovieLens 100K and MovieLens 1M. Further, content-based features are extracted from the dataset using ternary pattern and discrete wavelet transforms. After that hesitant fuzzy linguistic Bi-objective clustering (HFLBC) is applied for cluster selection based on the extracted features. Subsequently, a movie recommender scheme utilizing a convolutional spiking neural network is introduced to predict user film preferences. The efficiency of the proposed model is compared to existing methods such as multi-modal trust-dependent recommender scheme and graph-dependent hybrid recommendation scheme. The results show a significant improvement, with the proposed model achieving 13.79% and 16.47% higher accuracy than the existing methods. The findings highlight the potential of proposed system in enhancing the accuracy and personalization of movie recommendations.

Integrating Sentiment Analysis and Machine Learning for Improved Film Recommendation Systems

Abstract: To do so, especially when it comes to digital entertainment platforms, which are evolving rapidly, giving users options for having what they want, and the importance of personalization has simply gone up only. This project focuses on movie recommendations using sentiment analysis, which increases the accuracy of recommendations by adding review sentiments based on movie ratings and reviews. This project presents a movie recommendation system that leverages collaborative filtering and sentiment analysis to deliver more accurate suggestions to movie enthusiasts, specifically targeting "Cinemaniacs" and "Film Junkies.” The primary components of our approach include collaborative filtering, such as taking movie preferences from the user and performing natural language processing (NLP) techniques for sentiment analysis of user-generated reviews and ratings. By integrating user preferences, such as selected genres and viewing habits, with sentiment-driven insights from movie reviews, the system extends beyond traditional numeric ratings to capture nuanced satisfaction and dissatisfaction. The platform also includes genre-specific recommendations and predictive models that forecast upcoming movie releases based on individual tastes, trends, and pre-release sentiments. This innovative combination provides users with highly customized movie and web series suggestions, keeping them updated on new releases, while offering trailer predictions to preview potential interests. Through this multi-layered approach, the project aims to deepen viewer engagement by closely aligning content recommendations with emotional responses and genre preferences

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.

Research on Music Neighborhood-Based Recommendation Algorithms

This paper presents a comprehensive review of recommendation algorithms in the music domain. Music recommendation systems play a crucial role in delivering personalized content to users by analyzing patterns and preferences. We analyze several prominent recommendation algorithms, including collaborative filtering, content-based filtering, and hybrid models, each of which has been extensively applied to music recommendation tasks. The study also delves into the emerging techniques of deep learning and reinforcement learning in improving recommendation accuracy. A comparative analysis is provided, highlighting the strengths and limitations of each algorithm in terms of scalability, accuracy, and computational efficiency. Special attention is given to the challenges of balancing personalization and diversity in music recommendations. Furthermore, we explore how hybrid recommendation systems, which combine multiple methods, can overcome the limitations of individual models. The review concludes by identifying future research directions in the field of music recommendation systems, particularly the potential of leveraging more advanced machine learning techniques.

ENSG: Enhancing Negative Sampling in Graph Convolutional Networks for Recommendation Systems

In the field of recommendation, negative samples that are close to positive samples are referred to as “hard negative samples”. These hard negative samples are more likely to be incorrectly recommended to users. Therefore, researching how to enhance the ability to identify hard negative samples and thereby improve recommendation accuracy is an important direction in the field of recommendation systems. To address this issue, we propose a new model named Enhancing Negative Sampling in Graph Convolutional Networks for Recommendation Systems (ENSG). Firstly, part of the information in the positive sample was injected into the negative sample, and the high-quality, difficult negative sample was selected by the inner product method. Secondly, a lightweight graph convolutional network is used for feature extraction to obtain node representations for both users and items. Then, contrastive learning is used to maximize the similarity between the hard negative samples and the positive samples, so that the hard negative samples are as close to the positive samples as possible in the feature space. Ultimately, the model is trained by taking hard negative samples as input and minimizing the loss function to optimize model parameters; the recommendation accuracy of the model is enhanced. To validate the effectiveness of our approach, we conducted comparative evaluations utilizing three publicly accessible datasets. The experimental outcomes indicate that our proposed model surpasses the baseline model in terms of performance. On three public datasets, the algorithm proposed in this paper achieved the highest improvements of 16.27% and 12.72% in the evaluation metrics Recall@20 and NDCG@20, respectively.