Search

Recommender Systems (RSs) have recently emerged as a practical solution to the information overload problem users face when searching for digital content. In general, RSs provide their respective users with specialized advice and guidance in order to make informed decisions on the selection of suitable digital content. This paper is a systematic literature review of recent (2011–2023) publications on RSs designed and developed in the context of education to support teachers in particular—one of the target groups least frequently addressed by existing RSs. A body of 61 journal papers is selected and analyzed to answer research questions focusing on experimental studies that include RS evaluation and report evaluation results. This review is expected to help teachers in better exploiting RS technology as well as new researchers/developers in this field in better designing and developing RSs for the benefit of teachers. An interesting result obtained through this study is that the recent employment of machine learning algorithms for the generation of recommendations has brought about significant RS quality and performance improvements in terms of recommendation accuracy, personalization and timeliness. [ABSTRACT FROM AUTHOR]

Recommender systems are vulnerable to attacks because of their open nature. Counterfeit users give biased ratings to the items due to various objectives that may lead to the loss of user trust. The attackers use certain attack models with specific features. The existing attack detection techniques are typically attack-specific and work only when the attack features are known. They are unable to identify an unknown attack with unfamiliar features. To diminish this problem, in this paper, we propose a generalized solution that filters any attack irrespective of its design and features. We trained the classifiers with the ratings of the known authentic users using one-class SVM and PU learning models for detecting attacks, considering their ability to detect anomalies in the dataset caused by unknown attacks. The openly available MovieLens dataset has been used to assess our designed attack detection method. The experimental results show that all unknown attacks are successfully detected with 100% accuracy. The same detection accuracy is achieved for attacks with known features. [ABSTRACT FROM AUTHOR]

The study presents a Cluster-Based Cab Recommender System (CBCRS) designed to optimize cab services by suggesting the nearest locations with a higher likelihood of finding passengers. To achieve this, the system employs advanced clustering techniques to cluster historical cab pickup locations, identifying areas with higher passenger possibilities at specific times and days. The research aims to develop an algorithmic framework for CBCRS based on a hybrid clustering technique. The objectives of the study are twofold: first, to identify current clustering techniques used in clustering cab pickup geo-points, and second, to propose a framework for CBCRS based on the most efficient clustering technique. This framework will accept the current location of the cab driver and recommend the next nearest passenger pickup location. Additionally, the study compares and contrasts the proposed system with other clustering techniques using three standard datasets, evaluating them based on intrinsic measures such as the Calinski-Harabasz Index and Silhouette-Score. The paper concludes by evaluating and contrasting the proposed CBCRS framework with different clustering techniques, analyzing the results using statistical parameters. The findings reveal that the proposed CBCRS system generates better recommendations for the cab drivers using CBCRS hybrid clustering technique as compared to K-Means, BIRCH, DBSCAN clustering algorithms. [ABSTRACT FROM AUTHOR]

Continuous discovery and update of applications or their boundaries running in cloud environments in an automatic way is a highly required function of modern data center operation solutions. Prior attempts to address this problem within various products or projects were/are applying rule-driven approaches or machine learning techniques on specific types of data–network traffic as well as property/configuration data of infrastructure objects, which all have their drawbacks in effectively identifying roles of those resources. The current proposal (ADLog) leverages log data of sources, which contain incomparably richer contextual information, and demonstrates a reliable way of discriminating application objects. Specifically, using native constructs of VMware Aria Operations for Logs in terms of event types and their distributions, we group those entities, which then can be potentially enriched with indicative tags automatically and recommended for further management tasks and policies. Our methods differentiate not only diverse kinds of applications, but also their specific deployments, thus providing hierarchical representation of the applications in time and topology. For several applications under Aria Ops management in our experimental test bed, we discover those in terms of similarity behavior of their components with a high accuracy. The validation of the proposal paves the path for an AI-driven solution in cloud management scenarios. [ABSTRACT FROM AUTHOR]

In recent times, recommender systems have acquired significant popularity as a solution to the issue of information overload. These systems offer personalised recommendations to users. The superiority of multi-criteria recommender systems over their single-criterion counterparts has been demonstrated, as the former are able to provide more precise recommendations by taking into account multiple dimensions of user preferences when rating items. The prevalent recommendation technique, matrix factorization of collaborative filtering, is hindered by the data sparsity problem of the user-item matrix. On the other hand, it is noteworthy that deep learning techniques have demonstrated significant potential in various research domains, including but not limited to image processing, pattern recognition, computer vision, and natural language processing. In recent times, there has been a surge in the utilisation of deep learning techniques in recommender systems, yielding promising outcomes. This study presents a novel approach to multi-criteria recommender systems through the utilisation of deep learning algorithms to mitigate the data sparsity issue. Specifically, deep autoencoders are utilised to uncover complex, non-linear, and latent relationships between users' multi-criteria preferences followed by matrix factorization technique, ultimately leading to more precise recommendations. The proposed model is evaluated by conducting the experiments on the multi-criteria dataset of Yahoo! Movies. According to the outcomes, the proposed approach outperforms the state of the art recommendation methods by generating more accurate and personalized recommendations. Also, it reduces the data sparsity up to 11% from the multi-criteria dataset. [ABSTRACT FROM AUTHOR]

Tourism is an important sector, serving as an avenue to show the natural resources of a country and inhabitants' hospitality. This sector creates several opportunities for building a potential market and enhancing economic activities where tourist spots and activities flourish. Despite the numerous benefits, tourism still requires significant improvement, particularly in the Philippines, where there are abundant beautiful places. Therefore, this study aimed to develop a recommender system based on users and content collaborative filtering to provide local and foreign tourists with viable information for experience improvement. The investigation focused on improving tourist satisfaction based on three aspects such as preferences, ratings, and reviews that add options for tourist spots, activities/itineraries, destinations, and others. The machine algorithm-based journey assistant (MAJA) was designed as an interface and agent in providing help to tourists. The mean average precision (MAP) and recall were used as evaluation metrics to better understand the ability of MAJA to offer personalized experiences to unique users. The results showed that integration of the system into tourism provided a smart platform for enhancing tourist experience and destination competitiveness. Consequently, successful implementation of the system is measured by two criteria, namely the degree of tourists' pleasure during trip and the capacity of MAJA to effectively transfer tourism to less popular and less "accessible" sector. [ABSTRACT FROM AUTHOR]

In this paper, we propose to use a convertible deep neural network (DNN) model with a transfer adaptation mechanism to deal with varying input and output numbers of neurons. The flexible DNN model serves as a multi-label classifier for the recommender system as part of the retrieval systems' push mechanism, which learns the combination of tabular features and proposes the number of discrete offers (targets). Our retrieval system uses the transfer adaptation, mechanism, when the number of features changes, it replaces the input layer of the neural network then freezes all gradients on the following layers, trains only replaced layer, and unfreezes the entire model. The experiments show that using the transfer adaptation technique impacts stable loss decreasing and learning speed during the training process. Furthermore, our proposed model demonstrates notable advantages in production scenarios. Specifically, it exhibits enhanced efficiency, manifesting in accelerated processing times and improved resource utilization, thereby contributing to a more sustainable and cost-effective training of machine learning solutions in real-world applications. [ABSTRACT FROM AUTHOR]

The proliferation of uncategorized information on the Internet has intensified the need for effective recommender systems. Recommender systems have evolved from content-based filtering to collaborative filtering and, most recently, to deep learning-based and hybrid models. However, they often face challenges such as high computational costs, reduced reliability, and the Cold Start problem. We introduce a persona-based user modeling approach for real-time movie recommendations. Our system employs Non-negative Matrix Factorization (NMF) and Deep Learning algorithms to manage complex and sparse data types and to mitigate the Cold Start issue. Experimental results, based on criteria involving 50 topics and 35 personas, indicate a significant performance gain. Specifically, with 500 users, the precision@K for NMF was 86.01%, and for the Deep Neural Network (DNN), it was 92.67%. Tested with 900 users, the precision@K for NMF increased to 97.04%, and for DNN, it was 95.55%. These results represent an approximate 10% and 5% improvement in performance, respectively. The system not only delivers fast and accurate recommendations but also reduces computational overhead by updating the model only when user personas change. The generated user personas can be adapted for other recommendation services or large-scale data mining. [ABSTRACT FROM AUTHOR]

This study aimed to build a recommender system that predicts the shape of bacteria for biological requests of urine cytobacteriological examination (UCBE) using machine learning techniques, to reduce the time taken to identify the shape of bacteria (Cocci or Bacilli). We used different methods and techniques in the process: Unified Modelling Language (UML) was used for digital design architecture, Rstudio tool with R programming language for system development, and Random Forest (RF) algorithm for the prediction. Experimental results showed that the time needed to identify the shape of bacteria is decreased, and bacilli bacteria are better recognized by the algorithm with an error rate of 3%. In addition to that, the proposed recommender system allows biologists to validate and correct the prediction and improve the accuracy of the classification algorithm used in the future. [ABSTRACT FROM AUTHOR]

One of the methods most frequently used to recommend films is collaborative filtering. We examine the potential of collaborative filtering in our paper's discussion of product suggestions. In addition to utilizing collaborative filtering in a new application, the proposed system will present a better technique that focuses especially on resolving the cold start issue. The suggested system will compute similarity using the Pearson Correlation Coefficient (PCC). Collaborative filtering that uses PCC suffers from the cold start problem or a lack of information on new users to generate useful recommendations. The proposed system solves the issue of cold start by gauging each new user by certain arbitrary parameters and recommending based on the choices of other users in that demographic. The proposed system also solves the issue of users' reluctance to provide ratings by implementing a keyword-based perception system that will aid users in finding the right product for them. [ABSTRACT FROM AUTHOR]

Recommender systems position themselves as powerful tools in the support of relevance and personalization, presenting remarkable potential in the area of marketing. The cold-start customer problematic presents a challenge within this topic, leading to the need of distinguishing user features and preferences based on a restricted set of transactional information. This paper proposes a hybrid recommender system that aims to leverage transactional and portfolio information as indicating characteristics of customer behaviour. Four independent systems are combined through a parallelised weighted hybrid design. The first individual system utilises the price, target age, and brand of each product to develop a content-based recommender system, identifying item similarities. Secondly, a keyword-based content system uses product titles and descriptions to identify related groups of items. The third system utilises transactional data, defining similarity between products based on purchasing patterns, categorised as a collaborative model. The fourth system distinguishes itself from the previous approaches by leveraging association rules, using transactional information to establish antecedent and precedence relationships between items through a market basket analysis. Two datasets were analysed: product portfolio and transactional datasets. The product portfolio had 17,118 unique products and the included 4,408,825 instances from 2 June 2021 until 2 June 2022. Although the collaborative system demonstrated the best evaluation metrics when comparing all systems individually, the hybridisation of the four systems surpassed each of the individual systems in performance, with a 8.9% hit rate, 6.6% portfolio coverage, and with closer targeting of customer preferences and smaller bias. [ABSTRACT FROM AUTHOR]

Recommendation systems play a pivotal role in improving product competitiveness. Traditional recommendation models predominantly use centralized feature processing to operate, leading to issues such as excessive resource consumption and low real-time recommendation concurrency. This paper introduces a recommendation model founded on deep learning, incorporating edge computing and knowledge distillation to address these challenges. Recognizing the intricate relationship between the accuracy of deep learning algorithms and their complexity, our model employs knowledge distillation to compress deep learning. Teacher–student models were initially chosen and constructed in the cloud, focusing on developing structurally complex teacher models that incorporate passenger and production characteristics. The knowledge acquired from these models was then transferred to a student model, characterized by weaker learning capabilities and a simpler structure, facilitating the compression and acceleration of an intelligent ranking model. Following this, the student model underwent segmentation, and certain computational tasks were shifted to end devices, aligning with edge computing principles. This collaborative approach between the cloud and end devices enabled the realization of an intelligent ranking for product listings. Finally, a random selection of the passengers' travel records from the last five years was taken to test the accuracy and performance of the proposed model, as well as to validate the intelligent ranking of the remaining tickets. The results indicate that, on the one hand, an intelligent recommendation system based on knowledge distillation and edge computing successfully achieved the concurrency and timeliness of the existing remaining ticket queries. Simultaneously, it guaranteed a certain level of accuracy, and reduced computing resource and traffic load on the cloud, showcasing its potential applicability in highly concurrent recommendation service scenarios. [ABSTRACT FROM AUTHOR]

As one of the most pervasive applications of machine learning, recommender systems are playing an important role on assisting human decision-making. The satisfaction of users and the interests of platforms are closely related to the quality of the generated recommendation results. However, as a highly data-driven system, recommender system could be affected by data or algorithmic bias and thus generate unfair results, which could weaken the reliance of the systems. As a result, it is crucial to address the potential unfairness problems in recommendation settings. Recently, there has been growing attention on fairness considerations in recommender systems with more and more literature on approaches to promote fairness in recommendation. However, the studies are rather fragmented and lack a systematic organization, thus making it difficult to penetrate for new researchers to the domain. This motivates us to provide a systematic survey of existing works on fairness in recommendation. This survey focuses on the foundations for fairness in recommendation literature. It first presents a brief introduction about fairness in basic machine learning tasks such as classification and ranking to provide a general overview of fairness research, as well as introduce the more complex situations and challenges that need to be considered when studying fairness in recommender systems. After that, the survey will introduce fairness in recommendation with a focus on the taxonomies of current fairness definitions, the typical techniques for improving fairness, as well as the datasets for fairness studies in recommendation. The survey also talks about the challenges and opportunities in fairness research with the hope of promoting the fair recommendation research area and beyond. [ABSTRACT FROM AUTHOR]

In recent generations of the digital world medical data in Recommender Systems. Health Care Recommender System (HCRS) analyses the medical data and then predicts the user's or patient's illness. Nowadays, healthcare data is used by various users or patients in recommendation systems which are useful for everyone. Analysing and predicting medical data provides awareness to users and these data predictions may be enriched using various techniques of RS. Machine learning techniques are used to make sure that health data is reliable and of high quality. In every RS the issues are targeted such as scalability, sparsity and cold start problems. In many social networking applications, these issues are resolved using ML algorithms. However, there is a significant gap between IT systems and medical diagnosis. The fuzzy genetic method is used in HCRS in order to bridge the gap between IT and healthcare applications. Through the use of the mutation and crossover operators, a real-value genetic method is used in this to compute similarity. With the user's extra personalized information, fuzzy rules are later generated for the database. The Hybrid fuzzy-genetic method, also known as this situation, combines both techniques to improve recommendation quality. Utilizing this method will improve the quality of the recommendation process by discovering the most precise similarity measures among different users. Six factors are subjected to fuzzification, including age, gender, employment, height, weight, and region. Genre-interesting measure weights are then used, including Very Light, Light, Average, Heavy, and Very Heavy. Finally, the evaluation metrics used MAE and RMSE to evaluate the recommendation accuracy which showed the best results in comparison with baseline approaches such as Convolutional Neural Networks and Restricted Boltzman Machine. [ABSTRACT FROM AUTHOR]

Photovoltaic installations can be environmentally beneficial to a greater or lesser extent, depending on the conditions. If the energy produced is not used, it is redirected to the grid, otherwise a battery with a high ecological footprint is needed to store it. To alleviate this problem, an innovative recommender system is proposed for residents of smart homes equipped with battery-free solar panels to optimise the energy produced. Using artificial intelligence, the system is designed to predict the energy produced and consumed for the day ahead using three data sources: sensor logs from the home automation solution, data collected by the solar inverter, and weather data. Based on these predictions, recommendations are then generated and ranked by relevance. Data collected over 76 days were used to train two variants of the system, considering or without considering energy consumption. Recommendations selected by the system over 14 days were randomly picked to be evaluated for relevance, ranking, and diversity by 11 people. The results show that it is difficult to predict residents' consumption based solely on sensor logs. On average, respondents reported that 74% of the recommendations were relevant, while the values contained in them (i.e., accuracy of times of day and kW energy) were accurate in 66% (variant 1) and 77% of cases (variant 2). Also, the ranking of the recommendations was considered logical in 91% and 88% of cases. Overall, residents of such solar-powered smart homes might be willing to use such a system to optimise the energy produced. However, further research should be conducted to improve the accuracy of the values contained in the recommendations. [ABSTRACT FROM AUTHOR]

Faults recovery has recently emerged as an important aspect of web service composition (WSC) testing, as it aims to minimize the impact of faults on system functionality through restoring the system's operation after a fault has occurred. However, most of the existing recommendation systems (RSs) tend to recommend frequently used services, which lack diversity and face inaccuracies due to incomplete or biased historical data. In addition, the focus of the existing RSs is on proposing fault handling models rather than recommending the best recovery strategy for handling faults, with most being code-based, thus not suitable for WSCs. Accordingly, due to the opaque nature of WSCs with hidden source code, model-based recovery methods are preferred. In this paper, the Fault Recovery Strategies RS for WSCs (F2RS-WSC) is proposed to recommend the best recovery strategy for handling emerging faults in the WSCs paradigm. The proposed system is a model-based system that recommends the best strategy for recovering faulty paths generated from service dependency graphs (SDGs) based on the faults' types, severity levels, faults' location, as well as the time at which faults may occur. The experimental results show that the time consumed by F2RS-WSC to recommend the optimum recovery strategy represents less than 3% of the SDG parsing time and 4% of the path validation time. In addition, its superior performance assures its accuracy and efficiency. Thus, it achieves accuracy levels between 70% and 88 % among multiple datasets. Moreover, its average precision, recall and f-measure values are 0.85,0.81 and 0.86 respectively. [ABSTRACT FROM AUTHOR]

This paper proposes a recommendation system based on a hybrid learning approach for a personal deep sleep service, called the Customized Deep Sleep Recommender System (CDSRS). Sleep is one of the most important factors for human life in modern society. Optimal sleep contributes to increasing work efficiency and controlling overall well-being. Therefore, a sleep recommendation service is considered a necessary service for modern individuals. Accurate sleep analysis and data are required to provide such a personalized sleep service. However, given the variations in sleep patterns between individuals, there is currently no international standard for sleep. Additionally, service platforms face a cold start problem when dealing with new users. To address these challenges, this study utilizes K-means clustering analysis to define sleep patterns and employs a hybrid learning algorithm to evaluate recommendations by combining user-based and collaborative filtering methods. It also incorporates feedback top-N classification processing for user profile learning and recommendations. The behavior of the study model is as follows. Using personal information received through mobile devices and data, such as snoring, sleep time, movement, and noise collected through AI motion beds, we recommend sleep and receive user evaluations of recommended sleep. This assessment reconstructs the profile and, finally, makes recommendations using top-N classification. The experimental results were evaluated using two absolute error measurement methods: mean squared error (MSE) and mean absolute percentage error (MAPE). The research results regarding the hybrid learning methods show 13.2% fewer errors than collaborative filtering (CF) and 10.2% fewer errors than content-based filtering (CBF) on an MSE basis. According to the MAPE, the methods are 14.7% more accurate than the CF model and 9.2% better than the CBF model. These results demonstrate that CDSRS systems can provide more accurate recommendations and customized sleep services to users than CF, CBF, and combination models. As a result, CDSRS, a hybrid learning method, can better reflect a user's evaluation than traditional methods and can increase the accuracy of recommendations as the number of users increases. [ABSTRACT FROM AUTHOR]

Online shopping is a form of electronic commerce that enables customers to purchase products directly from the seller over the internet using a web browser or a mobile application. With the growing number of research papers on Deep Learning (DL)-based recommendations, DL models have proven to be effective in Recommender systems. Hence in this paper, relevant product accessories recommendation is proposed using deep learning and histogram features. The proposed recommendation describes the novel way of content-based filtering which divides the work into two phases. In phase 1, the implemented approach determines the color and category of the product. In phase 2, the recommendation system retrieves the matching accessories for the chosen product. For phase 1, Decision Tree, Linear Regression, Logistic Regression, Naïve Bayes, Long Short-Term Memory (LSTM), and a novel method of Stack dense Recurrent Neural Network (RNN) along with the color histogram is applied to identify the category and color of the product. It is justified that the proposed technique of stack dense RNN achieves 98% accuracy. In phase 2, from the Machine Learning (ML) perspective, Random Forest (RF) is employed for the recommendation. The RF model finds the matching accessories for the chosen product and retrieves the top relevant items. [ABSTRACT FROM AUTHOR]

Recommender System is a software tool that considers multiple parameters like the interest of a user, historical user data, browsing behavior, etc. to provide suitable recommendations. From e-commerce to social websites and from online research articles to entertainment, recommender systems have successfully rooted themselves in almost every application domain. Due to the popularity gain and people reliance on the recommendations generated in almost every domain, recommender systems have become vulnerable to online attacks known as shilling attacks or false rating attacks. An insight of recommender systems along with an analysis of shilling attacks is performed in this paper. These attacks are very common in social media to make the content popular among users by false ratings. Therefore, to find out the effect of false ratings, analysis of average, bandwagon attack, hybrid, and segment attacks are done on the basis of specificity, sensitivity, recall, precision and F-measure on Netflix and Movie lens dataset. These attacks should not affect food product items because most people purchase online items on the basis of ratings only. A good recommender system can overcome these attacks. Therefore, to deal with the above challenge of false ratings’ attack, an ensemble learning model has been proposed to classify the individuals which are most similar to the target user so that relevant recommendations are made to each user as well. The proposed approach is validated for dataset of the German online reviews/rating of organic coffee, to determine the customer demand for a particular brand of coffee using Machine learning algorithms. The comparative results show that proposed approach is better than Locally Deep Support Vector Machine,Neural Network, Logistic Regression, Bayes Point, and Decision Forest algorithms with an accuracy of 98 percent. [ABSTRACT FROM AUTHOR]

In the real-world, use of digital media is increasing day by day. Consumers are always in a dilemma when they have a lot of choices and they always get confused among them. The E-commerce companies want to increase their profit, so they introduced recommender systems. The recommender system is like the newspaper which gives us recommendations when we do not have any information about the particular products of the market. Users’ mind diverts the fetching of data from users’ favorite headlines just like the recommender system which fetches the items according to the users’ taste and preferences. However, to date Recommender systems have constraints of cold start problems, gray sheep user problems and shilling attacks. Variety in the tastes of the users gives rise to the gray sheep problem where it is difficult to match the products as per the choice of one person’s taste to the other person. This affects the performance of recommender systems. In this paper, the chocolate bars flavors_of_Cacao dataset (124KB) with 1796 entries tuples and 9 attributes dataset based on the personality parameters (modeling with Big Five model), is analyzed with boosted decision trees, two neural networks, logistic regression and decision forest. The accuracy of the decision forest is validated over other machine learning algorithms for a recommendation of the chocolate bars. [ABSTRACT FROM AUTHOR]

The inclusion of machine learning and ontology-based job recommender systems in the smart learning ecosystems may enhance the learners' employability in the regional context, by assisting learners to find jobs that match their skills and experience, and lead to a high level of professional satisfaction and high retention rates. The paper presents the CareProfSys job recommender system, developed by the authors, based on machine learning and ontology. The system analyses the learners' skills and interests and recommends suitable job opportunities, aligned with the regional occupational classifications. The recommendation generation mechanism is based on machine learning and ontology. The paper also presents the main further improvements in the system architecture and functionality. [ABSTRACT FROM AUTHOR]

Recommender systems have been successfully used in many domains with the help of machine learning algorithms. However, such applications tend to use multi-dimensional user data, which has raised widespread concerns about the breach of users’ privacy. Meanwhile, wearable technologies have enabled users to collect fitness-related data through embedded sensors to monitor their conditions or achieve personalized fitness goals. In this article, we propose a novel privacy-aware personalized fitness recommender system. We introduce a multi-level deep learning framework that learns important features from a large-scale real fitness dataset that is collected from wearable Internet of Things (IoT) devices to derive intelligent fitness recommendations. Unlike most existing approaches, our approach achieves personalization by inferring the fitness characteristics of users from sensory data, minimizing the need for explicitly collecting user identity or biometric information, such as name, age, height, and weight. Our proposed models and algorithms predict (a) personalized exercise distance recommendations to help users to achieve target calories, (b) personalized speed sequence recommendations to adjust exercise speed given the nature of the exercise and the chosen route, and (c) personalized heart rate sequence to guide the user of the potential health status for future exercises. Our experimental evaluation on a real-world Fitbit dataset demonstrated high accuracy in predicting exercise distance, speed sequence, and heart rate sequence compared with similar studies.1 Furthermore, our approach is novel compared with existing studies, as it does not require collecting and using users’ sensitive information. Thus, it preserves the users’ privacy. [ABSTRACT FROM AUTHOR]

The widespread use of E-commerce websites has drastically increased the need for automatic recommendation systems with machine learning. In recent years, many ML-based recommenders and analysers have been built; however, their scope is limited to using a single filtering technique and processing with clustering-based predictions. This paper aims to provide a systematic year-wise survey and evolution of these existing recommenders and analysers in specific deep learning-based hybrid filtering categories using movie datasets. They are compared to others based on their problem analysis, learning factors, data sets, performance, and limitations. Most contributions are found with collaborative filtering using user or item similarity and deep learning for the IMDB datasets. In this direction, this paper introduces a new and efficient Hybrid Filtering based Recommendation System using Deep Learning (HFRS-DL), which includes multiple layers and stages to provide a better solution for generating recommendations. [ABSTRACT FROM AUTHOR]

We implement a novel recommender system (RS) metaheuristic framework within a nonlinear NP-hard decision-making problem, for reducing the solution search space before high-burden computational steps are performed. Our RS-based metaheuristic supports consideration of comprehensive evaluation criteria, including estimations of the potential solution set's optimality, diversity, and feedback/preference of the end-user, while also being fully compatible with additional established RS evaluation metrics. Compared to prior Operations Research metaheuristics, our RS-based metaheuristic allows for (1) achieving near-optimal solution scores through comprehensive deep learning training, (2) fast metaheuristic parameter inference during solution instantiation trials, and (3) the ability to reuse this trained RS module for traditional RS ranking of final solution options for the end-user. When implementing this RS metaheuristic within an experimental high-dimensionality simulation environment, we see an average 91.7% reduction in computation time against a baseline approach, and solution scores within 9.1% of theoretical optimal scores. A simplified RS metaheuristic technique was also developed in a more realistic decision-making environment dealing with multidomain command and control scenarios, where a significant computation time reduction of 87.5% is also achieved compared with a baseline approach, while maintaining solution scores within 9.5% of theoretical optimal scores. [ABSTRACT FROM AUTHOR]

Low-rank matrix completion is a hot topic in the field of machine learning. It is widely used in image processing, recommendation systems and subspace clustering. However, the traditional method uses the nuclear norm to approximate the rank function, which leads to only the suboptimal solution. Inspired by the closed-form formulation of L 2 / 3 regularization, we propose a new truncated schatten 2/3-norm to approximate the rank function. Our proposed regularizer takes full account of the prior rank information and achieves a more accurate approximation of the rank function. Based on this regularizer, we propose a new low-rank matrix completion model. Meanwhile, a fast and efficient algorithm are designed to solve the proposed model. In addition, a rigorous mathematical analysis of the convergence of the proposed algorithm is provided. Finally, the superiority of our proposed model and method is investigated on synthetic data and recommender system datasets. All results show that our proposed algorithm is able to achieve comparable recovery performance while being faster and more efficient than state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recommender systems based on sentiment analysis become challenging due to the presence of enormous data available over the internet. With the lack of proper data cleaning and analysis methods, existing machine learning (ML) techniques fail to generate accurate recommendations. To overcome this issue, this paper proposes a Light Deep Learning (LightDL)-based recommender system that uses Twitter-based reviews. First, the data is collected from Twitter and cleaned by subsequent data cleaning processes. Then, this pre-processed data is fed into the LightDL model, which learns the important features like hashtags, unigrams, multigrams, etc. from each piece of data. Here, we have learned about four groups of features, including semantic features, syntactic features, symbolic features, and tweet-based features. Finally, the data is classified into positive, negative, and neutral categories according to the learned features. On the basis of classified sentiment, the review is generated to the users. Finally, the model is evaluated in terms of accuracy, precision, recall, f-measure, and error rate through extensive experiments in Matlab. The proposed LightDL model outperforms in all performance measures; specifically, it achieves 95% accuracy for the Twitter dataset. [ABSTRACT FROM AUTHOR]

Recent research works have shown the robustness towards the recommendation system for athletics using an AI automated system that enhances the longevity of the system. With this model, the automated recommendation helps to improve the quality of athletes during the process of training or other processes. Moreover, domain experts only can understand the rationale of the recommender system where the analyzed data is stored in the cloud system. This research proposes a machine learning–based solution for an athletic dataset that automatically predicts the state of the individual with features like age, gender, calories, temperature, pressure, heart rate, pulse rate, sugar level, respiratory conditions, and state of the body. This research concentrates on modeling a framework for implementing the machine learning approaches with an optimization problem. Here, a novel extreme multi-gradient evolutionary computation (EMGEC) with improved grey wolf optimization (IGWO) is proposed to achieve exploration and exploitation during the selection of features. The dataset collected from the athletes during the marathon (running) is collected from online resources and the feature subsets are extracted from the dataset. The features of these data are analyzed and encoded before placing it over the cloud environment. The performance of the proposed machine learning approach is compared with other approaches and provides better prediction accuracy, precision, recall, and F-measure respectively. The accuracy of the anticipated model is 83.13%, precision is 91.1%, and recall is 91.3% which is substantially higher than of other approaches. The proposed model shows a better trade-off in contrast to prevailing approaches like SVM, RF, k-NN, and logistic regression. [ABSTRACT FROM AUTHOR]

Recommender system (RS) is a suitable tool for filtering out items and providing the most relevant and suitable items to each user, based on their individual preferences. Deep learning algorithms achieve great success in several fields including RS. The issue with deep learning-based RS models is that, they ignore the differences of users' preferences, and they build a model based on all the users' rates. This paper proposed an optimized clustering-based denoising autoencoder model (OCB-DAE) which trains multiple models instead of one, based on users' preferences using k-means algorithm combined with a nature-inspired algorithm (NIA) such as artificial fish swarm algorithm to determine the optimal initial centroids to cluster the users based on their similar preferences, and each cluster trains its own denoising autoencoder (DAE) model. The results proved that combining NIA with k-means gives better clustering results comparing with using k-means alone. OCB-DAE was trained and tested with MovieLens 1M dataset where 80% of it is used for training and 20% for testing. Root mean squared error (RMSE) score was used to evaluate the performance of the proposed model which was 0.618. It outperformed the other models that use autoencoder and denoising autoencoder without clustering with 38.5% and 29.5% respectively. [ABSTRACT FROM AUTHOR]

Massive Open Online Courses (MOOCs) have significantly impacted the basic education industry since 2012. Online platforms enable learners to connect with the instructors present worldwide and reduce learning time by approximately 50-60%. Many universities have opted for their survival in the pandemic of COVID-19. During the pandemic, novice learners were not able to enroll in the relevant courses on these platforms, and instructors also faced challenges to satisfy their learners' needs. Each online forum has its own recommender system, and these systems only recommend courses from their own platforms. As a result, these platforms fail to satisfy the learners' educational needs and thereby increase the dropout ratio. The main objective of this study is to create a single platform for learners to search for courses from multiple platforms like Coursera, Udemy, EdX, Udacity, etc., and then recommend courses according to the learning behavior of a learner. A user profile is created in three ways, i.e., by registering, uploading their CV, or through their LinkedIn accounts. The recommender system then uses this user profile as input and recommends the relevant courses for user adaption. In this paper, demographic, content-based and collaboration-based recommender systems are used for recommendations. To validate, multi-model filtering, namely random, userbased collaboration, item-based collaboration, and matrix factorization, is used to obtain the values of the performance metrics such as RMSE, precision, and recall. On the basis of the results, the best result is obtained from user-based collaboration filtering on 6,000 dimensions of the dataset. The value of RMSE in the case of user-based collaboration filtering is 0.101, the value of precision is 0.82, and the value of recall is 0.822. Thus, the learner-centric hybrid filtering-based recommender system for MOOC platforms is implemented to enhance user adaptation. [ABSTRACT FROM AUTHOR]

In the futuristic Industry framework, user interactions with the product are seamlessly integrated with the product life cycle which results in Information overload. The shopbots were proposed in Industry 4.0 where the more focus was on process automation. In this research work, we propose recommender system for industry 5.0 which is based on collaboration of human beings and machines with more focus on user's personalization. Recommender system can be considered as an information filtering tool that provides suggestions to users about products, music, friend, topic, etc. This suggestion is based on the interest of users. Several research works have been carried out to improve recommendation accuracy by using matrix factorization, trust-based, hybrid-based, machine learning, and deep learning techniques. However, very few existing works have leveraged textual opinions for the recommendation to the best of our knowledge. Existing research works have focused only on numerical ratings, which do not reflect actual user behaviour. In this research work, sentiments of textual opinions are analysed for an in-depth analysis of user's behaviour. Recommendation accuracy is improved by using the proposed score Recop which is calculated from opinion sentiments. Furthermore, the sparsity issue is resolved by using our proposed approach. Amazon and Yelp review datasets are used for Experiment analysis. Mean absolute error (MAE) and root mean square error (RMSE) values are improved significantly using the proposed approach compared to the existing approaches. MAE and RMSE scores on the Yelp dataset are 0.85 and 1.51, respectively. Additionally, MAE and RMSE scores on the Amazon dataset are 0.66 and 0.93, respectively, which clearly reflects the significant contribution of our proposed approach. [ABSTRACT FROM AUTHOR]

This work introduced a novel approach for the movie recommender system using a machine learning approach. This work introduces a clustering-based approach to introduce a recommender system (RS). The conventional clustering approaches suffer from the clustering error issue, which leads to degraded performance. Hence, to overcome this issue, we developed an expectation-maximization-based clustering approach. However, due to imbalanced data, the performance of RS is degraded due to multicollinearity issues. Hence, we Incorporate PCA (Principal Component Analysis) based dimensionality reduction model to improve the performance. Finally, we aim to reduce the error; thus, a Genetic Algorithm (GA) is included to achieve the optimal clusters and assign the suitable recommendation. The experimental study is carried out on publically available movie datasets performance of the proposed approach is measured in terms of MSE (Mean Squared Error) and Root Mean Squared Error (RMSE). The comparative study shows that the proposed approach achieves better performance when compared with a state-of-art movie recommendation system. [ABSTRACT FROM AUTHOR]

Recommender Systems (RS) are used to generate recommendations of items that a user may be interested in. Several commercial wine recommender systems exist but are largely tailored to consumers outside of South Africa (SA). Consequently, these systems are of limited use to novice wine consumers in SA. In this research, a system soMLier (a combination of the terms 'sommelier' and 'Machine Learning') is developed for SA consumers that yields high-quality wine recommendations, maximises the accuracy of predicted ratings for those recommendations and provides insights into why those suggestions were made. This system is developed using two datasets – a database containing several attributes of SA wines and the corresponding numeric 5-star ratings made by users on Vivino.com. Using these datasets, several recommendation methodologies are investigated and it is found that collaborative filtering succeeds at generating lists of relevant wine recommendations, matrix factorisation techniques accurately predict ratings and content-based methods are most appropriate for explaining wine recommendations. These methods are optimally combined in the soMLier system. Though it would benefit from more explicit user data to establish a richer model of user preferences, soMLier can assist consumers in discovering wines they will likely enjoy and understanding their preferences of SA wine. Abbreviations: SA: South Africa(n); RS: Recommender System(s); IBCF: Item-basedCollaborative Filtering; CB: Content-Based; MF: Matrix Factorisation; RMSE: RootMean Square Error; COV: Coverage; PER: Personalistion; ARHR: Average ReciporcalHit Rate [ABSTRACT FROM AUTHOR]

Nowadays, e-learning and web-based learning are the most integrated new learning methods in schools, colleges, and higher educational institutions. The recent web-search-based learning methodological approach has helped online users (learners) to search for the required topics from the available online resources. The learners extracted knowledge from textual, video, and image formats through web searching. This research analyzes the learner's significant attention to searching for the required information online and develops a new recommendation system using machine learning (ML) to perform the web searching. The learner's navigation and eye movements are recorded using sensors. The proposed model automatically analyzes the learners' interests while performing online searches and the origin of the acquired and learned information. The ML model maps the text and video contents and obtains a better recommendation. The proposed model analyzes and tracks online resource usage and comprises the following steps: information logging, information processing, and word mapping operations. The learner's knowledge of the captured online resources using the sensors is analyzed to enhance the response time, selectivity, and sensitivity. On average, the learners spent more hours accessing the video and the textual information and fewer hours accessing the images. The percentage of participants addressing the two different subject quizzes, Q1 and Q2, increased when the learners attempted the quiz after the web search; 43.67% of the learners addressed the quiz Q1 before completing the web search, and 75.92% addressed the quiz Q2 after the web search. The average word counts analysis corresponding to text, videos, overlapping text or video, and comprehensive resources indicates that the proposed model can also apply for a continuous multi sessions online search learning environment. The experimental analysis indicates that better measures are obtained for the proposed recommender using sensors and ML compared with other methods in terms of recall, ranking score, and precision. The proposed model achieves a precision of 27% when the recommendation size becomes 100. The root mean square error (RMSE) lies between 8% and 16% when the number of learners < 500, and the maximum value of RMSE is 21% when the number of learners reaches 1500. The proposed recommendation model achieves better results than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Logistic regression is a very popular binary classification technique in many industries, particularly in the financial service industry. It has been used to build credit scorecards, estimate the probability of default or churn, identify the next best product in marketing, and many more applications. The machine learning literature has recently introduced several alternative techniques, such as deep learning neural networks, random forests, and factorisation machines. While neural networks and random forests form part of the practitioner's model-building toolkit, factorisation machines are seldom used. In this paper, we investigate the applicability of factorisation machines to some binary classification problems in banking. To stimulate the practical application of factorisation machines, we implement the fitting routines, based on logit loss and maximum likelihood, on commercially available software that is widely used by banks and other large financial services companies. Logit loss is usually used by the machine learning fraternity while maximum likelihood is popular in statistics. Depending on the coding of the target variable, we will show that these methods yield identical parameter estimates. Often, banks are confronted with predicting events that occur with low probability. To deal with this phenomenon, we introduce weights in the above-mentioned loss functions. The accuracy of our fitting algorithms is then studied by means of a simulation study and compared with logistic regression. The separation and prediction performance of factorisation machines are then compared to logistic regression and random forests by means of three case studies covering a recommender system, credit card fraud, and a credit scoring application. We conclude that logistic factorisation machines are worthy competitors of logistic regression in most applications, but with clear advantages in recommender systems applications where the number of predictors typically outnumbers the number of observations. [ABSTRACT FROM AUTHOR]

The growth of technology and social media websites has increased the potential to online explore different products and places around the globe. While online websites are primarily responsible for the generation of large amounts of data, this big data may be beneficial to other users provided the proper decision pattern can be analyzed. This work is focusing on the big data from social media to determine the travel destination preferences for Indian tourists. The analysis of online tourism reviews is beneficial to both tourists and businesses in tourist countries. Tourists can analyze all the required aspects prior to traveling and businesses in the destination country can enhance their products. The study aims to analyze the online tourist reviews using supervised machine learning methods (decision tree, k-nearest neighbor, back propagation neural networks and support vector machine) and ensemble learning in order to ascertain the travel preferences of Indian tourists visiting other countries. For the research experiments, significant travel data histories of tourists for the five destination places (Dubai, Indonesia, Malaysia, Thailand and Singapore) are extracted from TripAdvisor. TripAdvisor is a worldwide popular tourism website that provides access to consumers to share their travel experiences. From the selected five destination places, the preferences of Indian tourists are analyzed for the factors of travel & destination comfort, hotel facilities, food quality and attractions of the place. The analysis results of the proposed recommendation system indicate the determination of precise suggestions for Indian tourists traveling to other countries. [ABSTRACT FROM AUTHOR]

Recommender System is a information filtering tool to filter the relevant information from given information in the present era of big data. Movie Recommender System is machine learning based autonomous tool that filters the movies from big movie database like netflix, amazon etc according to user preferences. The main focus of this paper is Partitional Weighted co-clustering for Movie Recommender System. The primary objective of this research article is to fine tune the parameters of user and movie neighborhoods by setting different values for row clusters number and column clutsers number parameters of co-clustering. Test results obtained from the Movie database show that the proposed method can bring more accurate personalized recommendations for the movie as compared to existing methods of the order of 7.91%. [ABSTRACT FROM AUTHOR]

Literature survey shows that the recommendation systems have been largely adapted and evaluated in various domains. Due to low performances from various cyber attacks, the adoption of recommender system is in the initial stage of defense systems. One of the most common attacks for recommender system is shilling attack. There are some existing techniques for identifying the shilling attacks built in the user ratings patterns. The performance of ratings on target items differs between the attack user profiles and actual user profiles. To differentiate the certain profiles, the affected profiles are known as attack profiles. Besides the shilling attacks, real cyber attacks are taking place in the community which are being solved by Petri Net methods. These attacks can be falsely predicted (shilling attacks) by the users which can raise security threats. For identifying various shilling attacks without a priori knowledge, Recommendation System suffers from low accuracy. Basically, recommendation attack is split into nuke and push attack that encourage and discourage the recommended target item. The strength of shilling attack is usually measured by filler size and attack size. An experiment over unsupervised machine learning algorithms with filler size 3% over 3%, 5%, 8% and 10% attack sizes is presented for Netflix dataset. Furthermore, we conducted an experiment on data of 26 K videos on the Trending YouTube Video Statistics, to predict the user preferences for a particular genre of videos using Machine Learning Algorithms. Based on the results, it observed that the Boosted Decision tree performs the best with an accuracy of 99 percent. [ABSTRACT FROM AUTHOR]

The rapid growth of e-commerce has caused product overload where customers on the Web are no longer able to effectively choose the products they are exposed to. To overcome the product overload of online shoppers, a variety of recommendation methods have been developed. Collaborative Filtering (CF) is the most successful recommendation method, but its widespread use has exposed some well-known limitations, such as sparsity and scalability, which can lead to poor recommendations. This work proposes a recommendation methodology based on Web Usage Mining (WUM), and machine learning methods to enhance the recommendation quality and the system performance of current CF-based recommender systems. WUM populates the rating database by tracking learners' behaviors on the Web, thereby leading to better quality recommendations. The data is collected from user profile and their preferences and also the weblink and usage. Based on the CF and WUM data, the recommendations are provided. The Random Forest (RF) and Extreme Gradient Boosting (XGBoost) classifiers is used to improve the performance of searching for nearest neighbors through Shuffled Frog Leaping Algorithm (SFLA). Experimental results show that the proposed model is effective and can enhance the performance of recommendation. Results show that the proposed SFLA-XGBoost has higher average sensitivity: rating <=15 for CF by 11.49% for RF, by 7.52% for XGBoost and by 4.58% for proposed SFLA-RF respectively. [ABSTRACT FROM AUTHOR]

Knowledge graphs have been introduced into recommender systems due to the rich connectivity information. Many knowledge-aware recommendation methods use graph neural networks (GNNs) to capture the high-order structural and semantic information of knowledge graphs. However, previous GNN-based methods have the following limitations: (1) they fail to make full use of the neighborhood information of entities and (2) they ignore the importance of user interaction sequences on reflecting user preferences. As such, these models are insufficient for generating accurate representations of users and items. In this study, we propose a Knowledge-aware Hierarchical Attention Network (KHAN) to provide better recommendation. Specifically, the proposed model mainly consists of an item encoder and a user encoder. The item encoder is equipped with a hierarchical attention network, which is used to generate entity (item) representations by carefully aggregating neighborhood information of entities. The user encoder is also designed to learn more informative user representations from user interaction sequences using multi-head self-attention. The learned user representations are then combined with user representations introduced in the item encoder through a gating mechanism to generate the final user representations. Extensive experiments on two real-world datasets about movie and restaurant recommendation demonstrate the effectiveness of our model. [ABSTRACT FROM AUTHOR]

Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in the recommender systems. Recently, some deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. In these work, the attention mechanism is used to select the user interested items in historical behaviors, improving the performance of the CTR predictor. Normally, these attentive modules can be jointly trained with the base predictor by using gradient descents. In this paper, we regard user interest modeling as a feature selection problem, which we call user interest selection. For such a problem, we propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper. More specifically, we use a differentiable module as our wrapping operator and then recast its learning problem as a continuous bilevel optimization. Moreover, we use a meta-learning algorithm to solve the optimization and theoretically prove its convergence. Meanwhile, we also provide theoretical analysis to show that our proposed method 1) efficiencies the wrapper-based feature selection, and 2) achieves better resistance to overfitting. Finally, extensive experiments on three public datasets manifest the superiority of our method in boosting the performance of CTR prediction. [ABSTRACT FROM AUTHOR]

Clustering is one of the important stages of preliminary data analysis. It allows you to find patterns in them, to identify existing groups. For concert and theatre events, there are, as a rule, text data, such as: description of the event, name, etc. This article discusses the cluster analysis of events using their textual description. Using only text data, the resulting solution allows you to get a sufficient number of clusters. The results of the study can be useful, in particular, for development a recommendation system of concert and theater events. [ABSTRACT FROM AUTHOR]

Summary: The collaborative filtering (CF) recommendation algorithm predicts the purchases of specific users based on their characteristics and purchase history. This study empirically analyzes the possibility of applying CF to the insurance industry using real customer data from South Korea. Using three different CF models, we examined the relevance of applying the CF model to insurance products under various situations by comparing them with logistic‐regression‐based recommendation models. Through experiments, we empirically show that CF models apply to the insurance industry, especially when customer purchase information is added to the model. [ABSTRACT FROM AUTHOR]

The phenomenon of high dropout rates has been the concern of MOOC providers and educators since the emergence of this disruptive technology in online learning. This led to the focus on learner motivation studies from different aspects like demotivation signs detection, learning path personalization and course recommendation. Our paper aims to predict learner motivation for MOOCs to select the right MOOC for the right learner. Accordingly, we predict the motivation in an educational data mining approach by extracting and preprocessing learners' navigation traces on a MOOC platform, and building a Machine Learning model that predicts accurately a given learner's motivation for a MOOC. The comparison of the performance of four supervised learning algorithms resulted in the selection of the Random Forest classifier as the best modeling technique for motivation prediction with an accuracy of 95%. Afterward, we test the Machine Learning-based recommendation function for learners of the MOOC platform dataset to recommend the Top-10 MOOCs suitable for the target learner. Finally, further research on learner characteristics considered in recommender systems could enlarge the recommendation scope of MOOCs and maintain learner motivation. [ABSTRACT FROM AUTHOR]

Graph convolutional network (GCN)-based recommendation has recently attracted significant attention in the recommender system community. Although current studies propose various GCNs to improve recommendation performance, existing methods suffer from two main limitations. First, user-item interaction data is generally sparse in practice, highlighting these methods' ineffectiveness in learning user and item feature representations. Second, they usually perform a dot-product operation to model and calculate user preferences on items, leading to inaccurate user preference learning. To address these limitations, this study adopts a design idea that sharply differs from existing works. Specifically, we introduce the knowledge distillation concept into GCN-based recommendation and propose a two-phase knowledge distillation model (TKDM) improving recommendation performance. In Phase I, a self-distillation method on a graph auto-encoder learns the user and item feature representations. This auto-encoder employs a simple twolayer GCN as an encoder and a fully connected layer as a decoder. On this basis, in Phase II, a mutual-distillation method on a fully connected layer is introduced to learn user preferences on items with triple-based Bayesian personalized ranking. Extensive experiments on three realworld data sets demonstrate that TKDM outperforms classic and state-of-the-art methods related to GCN-based recommendation problems. [ABSTRACT FROM AUTHOR]

To solve the information explosion problem and enhance user experience in various online applications, recommender systems have been developed to model users’ preferences. Although numerous efforts have been made toward more personalized recommendations, recommender systems still suffer from several challenges, such as data sparsity and cold-start problems. In recent years, generating recommendations with the knowledge graph as side information has attracted considerable interest. Such an approach can not only alleviate the above mentioned issues for a more accurate recommendation, but also provide explanations for recommended items. In this paper, we conduct a systematical survey of knowledge graph-based recommender systems. We collect recently published papers in this field, and group them into three categories, i.e., embedding-based methods, connection-based methods, and propagation-based methods. Also, we further subdivide each category according to the characteristics of these approaches. Moreover, we investigate the proposed algorithms by focusing on how the papers utilize the knowledge graph for accurate and explainable recommendation. Finally, we propose several potential research directions in this field. [ABSTRACT FROM AUTHOR]

Recently, some attempts have been made in introducing deep neural networks (DNNs) to recommender systems for generating more accurate prediction due to the nonlinear representation learning capability of DNNs. However, they inevitably result in high computational and storage costs. Worse still, due to the relatively small number of ratings that can be fed into DNNs, they may easily suffer from the overfitting issue. To tackle these issues, we propose a novel recommendation framework based on Back Propagation (BP) neural network with attention mechanism, namely BPAM++. In particular, the BP neural network is utilized to learn the complex relationship between the target user and his/her neighbors and the complex relationship between the target item and its neighbors. Compared with DNNs, the shallow neural network, i.e., BP neural network, can not only reduce the computational and storage costs, but also alleviate the overfitting issues in DNNs caused by a relatively small number of ratings. In addition, an attention mechanism is designed to capture the global impact of the nearest users of the target user on their nearest target user sets. Extensive experiments conducted on eight benchmark datasets confirm the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Recommendation efficiency and data sparsity problems have been regarded as two challenges of improving performance for online recommendation. Most of the previous related work focus on improving recommendation accuracy instead of efficiency. In this paper, we propose a Deep Pairwise Hashing (DPH) to map users and items to binary vectors in Hamming space, where a user's preference for an item can be efficiently calculated by Hamming distance, which significantly improves the efficiency of online recommendation. To alleviate data sparsity and cold-start problems, the user-item interactive information and item content information are unified to learn effective representations of items and users. Specifically, we first pre-train robust item representation from item content data by a Denoising Auto-encoder instead of other deterministic deep learning frameworks; then we finetune the entire framework by adding a pairwise loss objective with discrete constraints; moreover, DPH aims to minimize a pairwise ranking loss that is consistent with the ultimate goal of recommendation. Finally, we adopt the alternating optimization method to optimize the proposed model with discrete constraints. Extensive experiments on three different datasets show that DPH can significantly advance the state-of-the-art frameworks regarding data sparsity and item cold-start recommendation. [ABSTRACT FROM AUTHOR]

The prediction of chronic diseases and their comorbidities is an essential task in healthcare, aiming to predict patients' future disease risk based on their previous medical records. The accumulation of administrative data has laid a solid foundation for applying deep learning approaches in healthcare. Existing studies focused on the patients' characteristics such as gender, age and location to predict the risk of the different diseases. However, there are high dimensional, incomplete and noisy problems in the administrative data. In this research, using administrative health data, we implemented graph theory and content-based recommender system approaches to analyse and predict chronic diseases and their comorbidities. Firstly, we used bipartite graphs to represent the relationships between patients and diseases. Then, we projected this graph to a one-mode graph, namely 'disease network'. After that, six recommender system models with patient features and network features were trained. The outputs of these models are the severity levels of diseases and the predicted diseases with rank. Finally, we evaluated the performance of these models against the same models without network features. The results demonstrated that the models with network features have lower prediction error and better performances for predicting chronic diseases and their latent comorbidities on large administrative data. Among these models, the graph convolution matrix completion model reveals the least amount of error and the best performance for prediction. Further, using a case study of a specific patient, we demonstrated the application of these models in predictive disease risk analysis. Thus, this study showed the potential application of the recommender system approaches to the health sector utilising administrative claim data, which could significantly contribute to healthcare services and stakeholders. [ABSTRACT FROM AUTHOR]

In recent years, many researchers take advantage of graph convolution network in multi-behavior recommendation to further alleviate the data sparsity problem. However, most of current works directly use graph convolution network, which makes time complexity of the model relatively high. These works also ignore the different weights of neighbors and the different contributions of each behavior to user' s preference . Therefore, this paper proposed a multi-behavior recommendation model based on light graph convolution and enhanced attention ( MB-LGCA) . Firstly, the model constructed a user-item bipartite graph according to the multi-behavior data, and used a light graph convolution network to aggregate the features of neighbors to obtain high-order collaborative information. At the same time, it used attention mechanism to integrate the neighbors' weights to enhance embedding representations of nodes . It used the k-order user 's embedding propagation to obtain the different importance of each behavior to user ' s preference, so that the model had better interpretability. Finally, it combined embedding representations of different layers for prediction. The experimental results on two real datasets show that the model has better performance. [ABSTRACT FROM AUTHOR]

The goal of the recommender system is to learn the user's preferences from the entity (user–item) historical interaction data, so as to predict the user's ratings on new items or recommend new item sequences to users. There are two major challenges: (1) Datasets are usually sparse. The item side is often accompanied by some auxiliary information, such as attributes or context; it can help to slightly improve its representation. However, the user side is usually presented in the form of ID due to personal privacy. (2) Due to the influences of confounding factors, such as the popularity of items, users' ratings on items often have bias that cannot be recognized by the traditional recommendation methods. In order to solve these two problems, in this paper, (1) we explore the use of a graph model to fuse the interactions between users and common rating items, that is, incorporating the "neighbor" information into the target user to enrich user representations; (2) the d o () operator is used to deduce the causality after removing the influences of confounding factors, rather than the correlation of the data surface fitted by traditional machine learning. We propose the EGCI model, i.e., enhanced graph learning for recommendation via causal inference. The model embeds user relationships and item attributes into the latent semantic space to obtain high-quality user and item representations. In addition, the mixed bias implied in the rating process is calibrated by considering the popularity of items. Experimental results on three real-world datasets show that EGCI is significantly better than the baselines. [ABSTRACT FROM AUTHOR]