Personalized Recommendations For Users Research Articles

Performance Evaluation on E-Commerce Recommender System based on KNN, SVD, CoClustering and Ensemble Approaches

E-commerce recommender systems (RS) nowadays are essential for promoting products. These systems are expected to offer personalized recommendations for users based on the user preference. This can be achieved by employing cutting-edge technology such as artificial intelligence (AI) and machine learning (ML). Tailored recommendations for users can boost user experience in using the application and hence increase income as well as the reputation of a company. The purpose of this study is to investigate popular ML methods for e-commerce recommendation and study the potential of ensemble methods to combine the strengths of individual approaches. These recommendations are derived from a multitude of factors, including users' prior purchases, browsing history, demographic information, and others. To forecast the interests and preferences of users, several techniques are chosen to be investigated in this study, which include Singular Value Decomposition (SVD), k-Nearest Neighbor Baseline (KNN Baseline) and CoClustering. In addition, several evaluation metrics including the fraction of concordant pairs (FCP), mean absolute error (MAE), root mean square error (RMSE) and normalized discounted cumulative gain (NDCG) will be used to assess how well different techniques work. To provide a better understanding, the outcomes produced in this study will be incorporated into a graphical user interface (GUI).

Performance Evaluation on E-Commerce Recommender System based on KNN, SVD, CoClustering and Ensemble Approaches

E-commerce recommender systems (RS) nowadays are essential for promoting products. These systems are expected to offer personalized recommendations for users based on the user preference. This can be achieved by employing cutting-edge technology such as artificial intelligence (AI) and machine learning (ML). Tailored recommendations for users can boost user experience in using the application and hence increase income as well as the reputation of a company. The purpose of this study is to investigate popular ML methods for e-commerce recommendation and study the potential of ensemble methods to combine the strengths of individual approaches. These recommendations are derived from a multitude of factors, including users' prior purchases, browsing history, demographic information, and others. To forecast the interests and preferences of users, several techniques are chosen to be investigated in this study, which include Singular Value Decomposition (SVD), k-Nearest Neighbor Baseline (KNN Baseline) and CoClustering. In addition, several evaluation metrics including the fraction of concordant pairs (FCP), mean absolute error (MAE), root mean square error (RMSE) and normalized discounted cumulative gain (NDCG) will be used to assess how well different techniques work. To provide a better understanding, the outcomes produced in this study will be incorporated into a graphical user interface (GUI).

Movie Recommendation System Using KNN, Cosine Similarity and Collaborative Filtering

The movie recommendation system is becoming increasingly popular in the digital era. With the continuous emergence of a vast amount of movie resources, users are facing more and more choices. Therefore, an intelligent movie recommendation system can assist users in quickly finding movies that match their personal preferences, thereby enhancing user satisfaction and movie-watching experience . Our movie recommendation system recommends high-rated and well-reviewed films and TV shows to the general audience based on Netflix viewers’ ratings for them. These are the movies and shows that are considered worth watching. We utilize the Netflix open dataset, which consists of a large number of user ratings and movie information [1]. By merging the movie and rating datasets and performing data cleansing and preprocessing, we obtain a dataset suitable for models. Subsequently, we represent the movie rating data using sparse matrices and train a k-nearest neighbours (k-NN) algorithm to achieve personalized movie recommendations [2].Our approach considers both user rating preferences and movie similarities, enabling accurate and personalized recommendations for users. Through evaluation experiments and user surveys, we validate the effectiveness of our recommendation system in terms of accuracy and user satisfaction [3]. This research is significant for improving the effectiveness of movie recommendation systems and enhancing user experiences.

Music Recommendation System using Collaborative Filtering with SVD

This research provides a music recommendation system that creates tailored recommendations for users based on their listening history using a collaborative filtering algorithm and Singular Value Decomposition (SVD). Initially, the research methodology attempted to use cosine similarity to generate recommendations, but it was found to be ineffective due to the inability to handle sparse matrices for large datasets. Therefore, the research shifted its approach to using SVD to overcome this issue. The Amazon Digital Music dataset is used for the implementation of the system, which contains user ratings and reviews for various music products. The dataset is divided into three matrices using the SVD algorithm: the user matrix, the song matrix, and the diagonal matrix. With the use of these matrices, it is possible to forecast missing ratings for unrated products. The predicted ratings are then used to generate personalized recommendations for the user. The Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE) metrics are used to gauge the system's performance. According to the evaluation's findings, the system performs admirably in terms of accuracy and efficacy, with low RMSE and MAE values. This indicates that the system can generate accurate recommendations for users based on their listening history, which can enhance the user experience and engagement with music streaming services. In conclusion, the work highlights the effectiveness of the collaborative filtering algorithm with SVD in generating personalized music recommendations for users. The failure of the initial approach using cosine similarity due to the inability to handle sparse matrices for large datasets underscores the importance of selecting appropriate algorithms for specific datasets. The proposed system demonstrates the effectiveness of using SVD for generating accurate and personalized recommendations for users, and future work could explore other machine learning techniques to further improve the system's performance.

Hybrid recommendation by incorporating the sentiment of product reviews

Hybrid recommender systems utilize advanced algorithms capable of learning heterogeneous sources of data and generating personalized recommendations for users. The data can range from user preferences (e.g., ratings or reviews) to item content (e.g., description or category).Prior studies in the field of recommender systems have primarily relied on “ratings” as the user feedback, when building user profiles or evaluating the quality of the recommendation. While ratings are informative, they may still fail to represent a comprehensive picture of actual user preferences. In contrast, there are other types of feedback data that differently or complementarily represent users and their preferences, including the reviews and the sentiments encapsulated within them. Such data can reveal important parts of a user’s profile that are not necessarily correlated with user ratings, and hence, they potentially reflect a different side of the user’s profile.In this paper, we propose a novel form of hybrid recommender system, capable of analyzing the reviews and extracting their sentiments that are incorporated into the recommendation process. We used advanced algorithms to generate recommendations for users capable of incorporating additional data, such as the review sentiment. We conducted analyses and showed that sentiments of user reviews are not always highly correlated with the ratings (e.g., in music domain). This might mean that sentiment can be indicative of a different aspect of user preferences and can be used as an alternative signal of user feedback. Hence, we have used both ratings and sentiments of reviews when evaluating our proposed hybrid recommender system. We selected two common datasets for the evaluation, Amazon Digital Music and Amazon Video Games, and showed the superior performance of the proposed hybrid recommender system compared to different baselines. The comparison were made in two evaluation scenarios, namely, when the ratings were considered the user feedback and when sentiments of the review were considered the user feedback.

Behavioral recommendation engine driven by only non-identifiable user data

Most recommendation systems utilize personal data to device personalized recommendations for users. Even though it seems favorable, security risks like data breaches are inevitable. This research proposes a novel reinforcement learning ‘approach’ to recommend users without collecting identifiable data. With only user activity on a session, our proposed method can model and track user behavior and formulate a recommendation system. We conclude that our algorithms demonstrate positive results in capturing user behavior without collecting private data of any kind from the user. The research is two folds. On one hand, we experiment using traditional reinforcement learning techniques (MDP, Q-learning), and on the other hand, we use deep reinforcement learning algorithms (DQN, DDQN, and D3QN) on a movie recommendation scenario. Interestingly, we observe that MDP and D3QN works comparatively better on movie recommendations.

Sequence Recommendation based on Deep Learning

Sequence recommendation systems have become increasingly popular in various fields such as movies and social media. These systems aim to predict a user's preferences and interests based on their past behavior and provide them with personalized recommendations. Deep learning, particularly Recurrent Neural Networks (RNNs), have emerged as a powerful tool for sequence recommendation. In this research, we explore the effectiveness of RNNs in movie and Instagram recommendation systems. We investigate and compare the performance of different types of RNNs, such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in recommending movies and Instagram posts to users based on their browsing history. Additionally, we study the impact of incorporating additional information such as user's demographics and Instagram hashtags on the performance of the recommendation system. We also evaluate the performance of RNN-based movie and Instagram recommendation systems in comparison to traditional approaches, such as collaborative filtering and content-based filtering, in terms of accuracy and personalization. The findings of this research provide insights into the effectiveness of RNNs in movie and Instagram recommendation systems and contribute to the development of more accurate and personalized recommendations for users.

Language interpretation in travel guidance platform: Text mining and sentiment analysis of TripAdvisor reviews.

The opinions and feelings expressed by tourists in their reviews intuitively represent tourists' evaluation of travel destinations with distinct tones and strong emotions. Both consumers and product/service providers need help understanding and navigating the resulting information spaces, which are vast and dynamic. Traditional sentiment analysis is mostly based on statistics, which can analyze the sentiment of a large number of texts. However, it is difficult to classify the overall sentiment of a text, and the context-independent nature limits their representative power in a rich context, hurting performance in Natural Language Processing (NLP) tasks. This work proposes an aspect-based sentiment analysis model by extracting aspect-category and corresponding sentiment polarity from tourists' reviews, based on the Bidirectional Encoder Representation from Transformers (BERT) model. First, we design a text enhancement strategy which utilizes iterative translation across multiple languages, to generate a dataset of 4,000 reviews by extending a dataset of 2,000 online reviews on 1,000 tourist attractions. Then, the enhanced dataset is reorganized into 10 classifications by the Term Frequency-Inverse Document Frequency (TF-IDF) method. Finally, the aspect-based sentiment analysis is performed on the enhanced dataset, and the obtained sentiment polarity classification and prediction of the tourism review data make the expectations and appeals in tourists' language available. The experimental study generates generic and personalized recommendations for users based on the emotions in the language and helps merchants achieve more effective service and product upgrades.

Quaternion-based knowledge graph neural network for social recommendation

In recent years, the surge in the number of users in recommender systems has brought unprecedented opportunities and challenges to research on recommender systems. The development of the graph neural network makes social recommendation based on graph data more advantageous, but it also brings problems with parameterization. Although the recommender system contains a large amount of data, such as users, items, and user-item interactions, the social relationship data of users in social recommendation are still sparse. To solve the problem of parameterization, we propose a novel quaternion-based knowledge graph neural network for social recommendation (QSoR), which applies hypercomplex space to the social recommendation. Without affecting the recommendation quality, QSoR utilizes the expressibility of the quaternion and weight sharing mechanism of the Hamilton product to reduce the parameters during training. To solve the problem of the sparsity of users’ social relationship data, we propose a quaternion-based explicit and implicit social relationships integration algorithm, which obtains users’ implicit social relationships from the user-item graph as a supplement for users’ social information. We design a double-end attention mechanism when obtaining the user’s preferences and social relationships, which makes full use of the item information and the interaction information between the user and the neighbor nodes. In this way, we can obtain users’ personalized preferences, distinguish the importance of user relationships, and obtain neighbors with a high degree of influence on users, thus improving the accuracy of recommendation results. The social relationship graph and the user-item graph are effectively combined in the quaternion space to make personalized recommendations for users. Experiments on three public datasets, Yelp, Last-FM, and Epinions, demonstrate the validity of the proposed model QSoR.

Using neural networks with reinforcement in the tasks of forming user recommendations

The article discusses the design of an algorithm for the formation of personalized user recommendations. The basis of the algorithm is a recurrent neural network with reinforcement. The use of neural networks in the recommendation algorithm will help to increase persistence as it becomes possible to identify weak relationships of implicit factors.

Diversity in news recommendations using contextual bandits

Contextual bandit techniques have recently been used for generating personalized user recommendations in situations where collaborative filtering based algorithms may be inefficient. They are often used in cases when input data are dynamically changing as new users and content items, such as news, constantly change. Contextual bandit methods sequentially select articles for recommendation to a user and continuously modify their strategies so as to present users with articles that maximize clicks. However, exclusively focusing on maximizing the number of clicks can lead to over-exposure of certain articles, while under-representing others. In an era of ever growing demand for digital news delivery, this, in turn, invokes the important notion of presenting news content to users in a “socially responsible” way. To this effect, we introduce a technique based on the contextual bandit framework that, in addition to maximization of the click rate, also considers historical frequency of an article as the “cost” associated with recommending it. It is demonstrated that this approach results in a more balanced distribution and a diverse set of recommended articles. Experiments utilizing a benchmark news dataset demonstrate the trade-off between clicks and diversity of recommended articles.

Enhancing rating prediction for recommendation by metric learning with gray relational analysis

PurposeThe purpose of the paper is to improve the rating prediction accuracy in recommender systems (RSs) by metric learning (ML) method. The similarity metric of user and item is calculated with gray relational analysis.Design/methodology/approachFirst, the potential features of users and items are captured by exploiting ML, such that the rating prediction can be performed. In metric space, the user and item positions can be learned by training their embedding vectors. Second, instead of the traditional distance measurements, the gray relational analysis is employed in the evaluation of the position similarity between user and item, because the latter can reduce the impact of data sparsity and further explore the rating data correlation. On the basis of the above improvements, a new rating prediction algorithm is proposed. Experiments are implemented to validate the effectiveness of the algorithm.FindingsThe novel algorithm is evaluated by the extensive experiments on two real-world datasets. Experimental results demonstrate that the proposed model achieves remarkable performance on the rating prediction task.Practical implicationsThe rating prediction algorithm is adopted to predict the users' preference, and then, it provides personalized recommendations for users. In fact, this method can expand to the field of classification and provide potentials for this domain.Originality/valueThe algorithm can uncover the finer grained preference by ML. Furthermore, the similarity can be measured using gray relational analysis, which can mitigate the limitation of data sparsity.

Restaurant Recommendation System using Machine Learning

Nowadays a big challenge when going out to a new restaurant or cafe, people usually use websites or applications to look up nearby places and then choose one based on an average rating. But most of the time the average rating isn't enough to predict the quality or hygiene of the restaurant. Different people have different perspectives and priorities when evaluating a restaurant. Many online businesses now have implemented personalized recommendation systems which basically try to identify user preferences and then provide relevant products to enhance the users experience . In turn, users will be able to enjoy exploring what they might like with convenience and ease because of the recommendation results. Finding an ideal restaurant can be a struggle because the mainstream recommender apps have not yet adopted the personalized recommender approach. So we took up this challenge and we aim to build the prototype of a personalized recommender system that incorporates metadata which is basically the information provided by interactions of customers and restaurants online(reviews), which gives a pretty good idea of customers satisfaction and taste as well as features of the restaurant. This type of approach enhances user experience of finding a restaurant that suits their taste better. This paper has used a package called lightfm(the library of python for implementing popular recommendation algorithms) and the dataset from yelp. There are different methods of filtering the data, here we have used Hybrid filtering which is a combination of Content-based filtering (CBF) and Collaborative Filtering (CF). Since the results from Hybrid filtering are far more closer to accuracy than CBF or CF respectively. Then hybrid filtering gives results in the form of personalized recommendations for users after training and testing of the data

Research and Implementation of Electronic Commerce Intelligent Recommendation System Based on the Fuzzy Rough Set and Improved Cellular Algorithm

With the continuous development of e-commerce, our society has transitioned from a mechanical era to an intelligent era. There have been many things that have subverted people’s traditional concepts, and they have also completely changed the way of life of modern people. Due to the development of e-commerce, people can enjoy the scenery and food from all over the world at home. Online shopping and online ticket purchase have greatly facilitated people’s lives and given people more choices. However, due to the excessive selection of things, there is also a phenomenon of information overload. Sometimes, it is difficult for people to find a product or content that they are very satisfied with. So, how to analyze people’s browsing behavior and predict what kind of content people want and how to push products on major websites have become a major issue facing major online companies. Based on this, this paper proposes an e-commerce intelligent recommendation technology based on the fuzzy rough set and improved cellular algorithm. It provides personalized recommendations for users based on their browsing history and purchase history. The research of this article is mainly divided into four parts. The first part is to analyze the status quo of technical research in this field. By analyzing the shortcomings of the existing technology, the concept of this article is proposed. The second part introduces the classic intelligent recommendation algorithm, including the principle and process of the fuzzy rough set and improved honeycomb algorithm, and analyzes the difference of various recommendation algorithms to illustrate the adaptability of each algorithm in practical applications and their respective advantages and disadvantages. The third part introduces an intelligent recommendation system based on fuzzy clustering, comprehensively analyzes the characteristics of users and commodities, makes full use of users’ evaluation information of commodities, and realizes intelligent recommendation based on content and collaborative filtering. At the end of the article, through comparative analysis experiments, the superiority of the intelligent recommendation system for electronic commerce based on the fuzzy rough set and improved cellular algorithm is further proved, and the accuracy of intelligent recommendation is improved.

Graph Neural Network and Context-Aware Based User Behavior Prediction and Recommendation System Research.

Due to the influence of context information on user behavior, context-aware recommendation system (CARS) has attracted extensive attention in recent years. The most advanced context-aware recommendation system maps the original multi-field features into a shared hidden space and then simply connects it to a deep neural network (DNN) or other specially designed networks. However, for different areas, the ability of modeling complex interactions in a sufficiently flexible and explicit way is limited by the simple unstructured combination of feature fields. Therefore, it is hard to get the accurate results of the user behavior prediction. In this paper, a graph structure is used to establish the interaction between context and users/items. Through modeling user behavior, we can explore user preferences in different context environments, so as to make personalized recommendations for users. In particular, we construct a context-user and context-item interactions graph separately. In the interactions graph, each node is composed of a user feature field, an item feature field, and a feature field of different contexts. Different feature fields can interact through edges. Therefore, the task of modeling feature interaction can be transformed into modeling the node interaction on the corresponding graph. To this end, an innovative model called context-aware graph neural network (CA-GNN) model is designed. Furthermore, in order to obtain more accurate and efficient recommendation results, first, we innovatively use the attention mechanism to improve the interpretability of CA-GNN; second, we innovatively use the degree of physical fatigue features which has never been used in traditional CARS as critical contextual feature information into our CA-GNN. We simulated the Food and Yelp datasets. The experimental results show that CA-GNN is better than other methods in terms of root mean square error (RMSE) and mean absolute error (MAE).

Multi-view visual Bayesian personalized ranking for restaurant recommendation

In recent recommendation systems, the image information of items is often used in conjunction with deep convolution network to directly learn the visual features of items. However, the existing approaches usually use only one image to represent an item. These approaches are inadequate for an item with multi-view related images. For a restaurant, it has visual information of food, drink, environment, and so on. Each view of an item can be represented by multiple images. In this paper, we propose a new factorization model that combines multi-view visual information with the implicit feedback data for restaurant prediction and ranking. The visual features (visual information) of images are extracted by using a deep convolution network and are integrated into a collaborative filtering framework. In order to conduct personalized recommendation better, the multi-view visual features are fused through user related weights. User related weights reflect the personalized visual preference for restaurants and the weights are different and independent between users. We applied this model to make personalized recommendations for users on two real-world restaurant review datasets. Experimental results show that our model with multi-view visual information achieves better performance than models without or with only single-view visual information.

Research on Collaborative Filtering Recommendation Algorithm Based on Mahout and User Model

Based on the research status of recommendation system, the traditional collaborative filtering algorithm is explored. By establishing the concept of training sample and Mahout framework, a collaborative filtering algorithm based on Mahout and extracted user model can be proposed. Using this algorithm in the system of recommendation aims to solve the problem of transforming the traditional recommendation problem into the classification problem in machine learning. In this way, it can provide personalized recommendations for users. The analysis of the experimental results of the collected some data sets suggests that the algorithm based on user model and machine learning is effective and optimal, at the same time, the efficiency of the algorithm under Mahout framework is also verified.

Privacy Preserving Profile Matching System for Trust-Aware Personalized User Recommendations in Social Networks

Privacy Preserving Profile Matching System for Trust-Aware Personalized User Recommendations in Social Networks

A Review on Trust-Aware and Privacy Preserving Profile Matching System for Personalized User Recommendations in Social networks

is becoming a very important part of social network from the security point of view. In this project, we introduce a framework for handling trust in social networks, which is based on reputation mechanism. The reputation mechanism captures the implicit and explicit connections between the network members, analyses the semantics and dynamics of these connections, and provides personalized user recommendations to the network members. Based on the trust semantics, the system will provide the positive (trustworthy) recommendations and the negative (untrustworthy) recommendations. Along with this our system provides one more interesting mode i.e. public profile matching that preserves privacy on social networks. This profile matching contributes in reputation ratings required for suggestions of friend list. In order to compute the reputation of each member, we adopt several other properties of trust such as, transitivity, personalization, and context, and draw ideas from sociology axioms. Trust is not perfectly transitive in social networks, in that trust decays along the transition path, but it is generally agreed that it can be communicated between people. Along with trust generation percentile of profile matching is also considered for personal recommendation.

A Trust-Aware System for Personalized User Recommendations in Social Networks

Social network analysis has recently gained a lot of interest because of the advent and the increasing popularity of social media, such as blogs, social networking applications, microblogging, or customer review sites. In this environment, trust is becoming an essential quality among user interactions and the recommendation for useful content and trustful users is crucial for all the members of the network. In this paper, we introduce a framework for handling trust in social networks, which is based on a reputation mechanism that captures the implicit and explicit connections between the network members, analyzes the semantics and dynamics of these connections, and provides personalized user recommendations to the network members.