Optimizing collaborative filtering recommender systems with the GRPO reinforcement learning algorithm

Recommender systems provide users with product information and suggestions, which has gradually become an important research tool in e-commerce IT technology, which has attracted a lot of attention of researchers. Collaborative filtering recommendation technology has been the most successful recommendation technology so far, but there are two major problems—recommendation quality and scalability. At present, research at home and abroad mainly focuses on recommendation quality, and there is less discussion on scalability. The scalability problem is that as the size of the system increases, the response time of the system increases to a point where users cannot afford it. Existing solutions often result in a significant drop in recommendation quality while reducing recommendation response time. In this paper, the clustering analysis subsystem based on the genetic algorithm is innovatively introduced into the traditional collaborative filtering recommendation system, and its design and implementation are given. In addition, when obtaining the nearest neighbors, only the clustered users of the target user are searched, making it a collaborative filtering recommender system based on genetic clustering. The experimental results show that the response time of the traditional collaborative filtering recommender system increases linearly with the increase in the number of users while the response time of the collaborative filtering recommender system based on genetic clustering remains unchanged with the increase in the number of users. On the other hand, the recommendation quality of the collaborative filtering recommender system based on genetic clustering is basically not degraded compared with that of the traditional collaborative filtering recommender system. Therefore, the collaborative filtering recommender system based on genetic clustering can effectively solve the scalability problem of the collaborative filtering recommender system.

Los sistemas de recomendación han tenido un rápido crecimiento tanto en investigación académica como en aplicaciones industriales en los últimos años. Las recomendaciones se nos proporcionan cuando elegimos elementos como música, películas, restaurantes, noticias, etc. Como parte de las técnicas de recomendación más prometedoras, los sistemas basados en recomendación de filtros colaborativos desempeñan un papel importante en las aplicaciones actuales. La aparición de nuevas fuentes de información requiere la combinación de sistemas de recomendación con técnicas avanzadas de otros campos, como el análisis de redes sociales, el procesamiento del lenguaje natural, el aprendizaje en profundidad, etc. Esta combinación mejora la calidad de las recomendaciones. Los sistemas de recomendación anteriores se centran principalmente en las mejoras de la precisión de la recomendación. Recientemente, surge una tendencia para la evaluación del rendimiento de los sistemas de recomendación que toma muchas propiedades nuevas en consideración. La fiabilidad es uno de los aspectos más notables y será profundamente estudiado en esta tesis. Se han propuesto algunas medidas para medir la fiabilidad de los sistemas de recomendación de filtrado colaborativo basados en la memoria. Sin embargo, observamos un área sin cubrir en el diseño de las medidas de fiabilidad adecuadas para los sistemas de recomendación de filtros colaborativos basados en modelos, especialmente aquellos basados en la factorización matricial. También encontramos que hay una falta de medidas de calidad de fiabilidad adecuadas. Esta tesis se concentra en proporcionar soluciones a ambas ausencias. Después de un estudio exhaustivo de trabajos de investigación del estado del arte, proponemos una nueva medida de fiabilidad que supera los desafíos de generalización y abstracción causados por los factores latentes de los métodos de factorización matricial. La medida propuesta se compara con con métodos y algoritmos representativos, usando bases de datos publicas, tanto académicas como comerciales. Los resultados experimentales muestran que nuestra nueva medida logra mejoras en la calidad de la recomendación. Además, la medida de fiabilidad propuesta también tiene un impacto muy positivo contra los "Shilling Attacks". Para obtener una mejora respecto a las medidas existentes de calidad de la fiabilidad, también proponemos, hasta donde sabemos, la primera medida de calidad de fiabilidad universal que es capaz de proporcionar valores numéricos para cualquier tipo de sistema de recomendación. Esta medida también se ha probado usando conjuntos de datos públicos reales y ha sido comparada con los métodos de calidad de la fiabilidad existentes. Basándonos en los resultados de los experimentos, concluimos que nuestra medida supera los últimos trabajos de investigación, proporcionando valores de calidad de fiabilidad más precisos e informativos. ----------ABSTRACT---------- Recommender systems have experienced a rapid growth in both academical research and industrial applications in latest years. Recommendations are provided to us when we choose items such as music, movies, restaurants, news, etc. As the most promising recommendation techniques, collaborative filtering recommender systems play an important role in current applications. The emergence of novel information sources requires to combine recommender systems with several advanced techniques coming from other fields like social network analysis, natural language processing, deep learning etc. This combination improves the quality of recommendations. Previous recommender systems research mainly focuses on the improvements of recommendation accuracy. Recently a new trend arises for the performance evaluation of recommender systems that takes many novel properties into consideration. Reliability is one of the most remarkable aspects, which will be deeply studied in this thesis. Some measures have been proposed for measuring reliability of memory based collaborative filtering recommender systems. However, we observe a gap in the design of proper reliability measures for model based collaborative filtering recommender systems, especially those based on matrix factorization. We also found that there is a lack in proper reliability quality measures. This thesis concentrates on providing solutions to both lacks. After a comprehensive study of state-of-the-art research works, we propose a novel reliability measure that overcomes the challenges of generality and abstraction caused by latent factors of matrix factorization methods. The proposed measure is tested against current baselines on public academic and commercial datasets; experiment results show that our novel measure achieves better improvements on recommendation quality. What’s more, the proposed reliability measure also has a very positive impact against shilling attacks. In order to fill in the blank of reliability quality measures, we also propose, as far as we know, the first universal reliability quality measure that is able to provide numerical values for any type of recommender systems. This measure has also been tested on public academic and commercial datasets using current methods. Based on the experiment results we conclude that our quality measure outperforms state-of-the-art research works by providing more accurate and informative reliability quality values.

With the rapid development of e-commerce, collaborative filtering recommendation system has been widely used in various network platforms. Using recommendation system to accurately predict customers’ preferences for goods can solve the problem of information overload faced by users and improve users’ dependence on the network platform. Because the recommendation system based on collaborative filtering technology has the ability to recommend more abstract or difficult to describe goods in words, the research related to collaborative filtering technology has attracted more and more attention. According to the past research, in collaborative filtering algorithm, if Pearson correlation coefficient is used, errors will occur under special circumstances. In this study, the normal recovery similarity measure is used to modify the similarity value to correct the error value of a collaborative filtering recommendation algorithm. Based on this, a big data analysis method based on a modified collaborative filtering recommendation algorithm is proposed. This research implemented it in the cloud Hadoop environment, and measure the execution time with 2, 5 and 8 nodes. Then the research compared it with the execution time of a single machine, and analyze its speedup ratio and efficiency. The experimental results show that the execution time increases with the number of neighbors. When the number of nodes is 5 and 8, the execution time is greatly improved, which improves the efficiency of collaborative filtering algorithm and can cope with massive data in the future.

The available data on the Internet can be utilized to obtain valuable information on any given subject. But the data is massive and intricate, which produces many problems for users in finding information of their interests. Recommender Systems (RSs) are successful software techniques designed to solve this issue. The RSs have a broad range of uses, such as providing consumers with a suggested list of products for online shopping, recommending articles or books for reading online, film or music recommendations, media recommendations, and so on. The traditional Collaborative Filtering (CF) recommender systems use different item ratings as a foundation to recommend new items to various users. The sparsity of this user-item matrix affects the performance of RS. Also, most consumers on today's e-commerce websites would not purchase a product that they do not find appealing, even though it has especially favorable feedback. As a result, we can say that consumers give equal importance to product images and the item's ratings. This paper aims to research to improve the traditional collaborative filtering recommender system by imbibing visual characteristics with explicit feedback (ratings). The visual features are extracted using transfer learning with the convolutional neural network (CNN). The amazon product dataset for clothing, shoes, and jewelry is used to validate the proposed approach. The results are compared using standard evaluation measures like MAE and RMSE.KeywordsCollaborative filteringRecommender systemConvolutional neural networkTransfer learning

Recommender Systems are used for finding the needle in the haystack. Recommender systems are of one the innovations in this revolution, which addresses the problem of filtering the data/information that is more likely to. Collaborative filtering is a technique which makes automatic predictions, by collecting the preferences for the users. But collecting the preferences from the user is no easy task. The Collaborative Filtering can also be a user based k-NN collaborative filtering algorithm or an item based k-NN collaborative filtering algorithm. Each type has its merits and demerits. Aiming at this concern, an ensemble based k-NN collaborative filtering is proposed. This work fuses the merits of the user based k-NN algorithm and item-based algorithm. The experiment analysis on the MovieLens dataset gives a consistent model that is accurate and results in better personalized movie recommendations than other conventional models. The experimental results show that ensemble based k-NN algorithm clearly improves enhances the recommender system's performance, and give better recommendation quality.

Currently the use of web recommendation techniques is growing worldwide with aim of providing the custom-made required data to end users. Most of the web users complain about finding useful information on web sites. Web recommender systems predict the information needs of users and provide them with recommendations to facilitate their navigation. Recommender systems have been extensively explored in web mining. The web recommendation systems are split into two main categories such as collaborative recommendation system and content based recommendation system. However, the quality of recommendations and the user satisfaction with such systems are still not optimal. In adaptive association recommender systems based on web mining techniques have strengths and weaknesses. One of these weaknesses is lack of consideration of an appropriate measure to calculate the user’s interest degree of pages. Applying Fuzzy Association Rule Mining (FARM) algorithm to a recommender system leads to calculate user’s interest of pages more accurately. Consequently generated recommendations will be more desirable when compared to other association rule mining techniques.

Nowadays, collaborative filtering recommender systems have been widely deployed in many commercial companies to make profit. Neighborhood‐based collaborative filtering (CF) is common and effective. To date, despite its effectiveness, there has been little effort to explore their robustness and the impact of data poisoning attacks on their performance. Can the neighborhood‐based recommender systems be easily fooled? To this end, we shed light on the robustness of neighborhood‐based recommender systems and propose a novel data poisoning attack framework, encoding the purpose of attack and constraint against them. We first illustrate how to calculate the optimal data poisoning attack, namely, UNAttack. We inject a few well‐designed fake users into the recommender systems such that target items will be recommended to as many normal users as possible. Extensive experiments are conducted on three real‐world datasets to validate the effectiveness and the transferability of our proposed method. In addition, some interesting phenomena can be found. For example, (i) neighborhood‐based recommender systems with Euclidean distance‐based similarity have strong robustness and (ii) the fake users can be transferred to attack the state‐of‐the‐art CF recommender systems such as neural CF and Bayesian personalized ranking matrix factorization.

Collaborative filtering (CF) technique in recommender systems (RS) is a well-known and popular technique that exploits relationships between users or items to make product recommendations to an active user. The effectiveness of existing memory based algorithms depend on the similarity measure that is used to identify nearest neighbours. However, similarity measures utilize only the ratings of co-rated items while computing the similarity between a pair of users or items. In most of the e-commerce applications, the rating matrix is too sparse since even active users of an online system tend to rate only a few items of the entire set of items. Therefore, co-rated items among users are even sparser. Moreover, the ratings a user gives an individual item tells us nothing about his comprehensive interest without which the generated recommendations may not be satisfactory to a user. In order to be able to address these issues, a comprehensive study is made of the various existing measures of similarity in a collaborative filtering recommender system (CFRS) and a hierarchical categorization of products has been proposed to understand the interest of a user in a wider scope so as to provide better recommendations as well as to alleviate data sparsity.

“Shilling” attacks or “profile injection” attacks have always major challenges in collaborative filtering recommender systems (CFRSs). Many efforts have been devoted to improve collaborative filtering techniques which can eliminate the “shilling” attacks. However, most of them focused on detecting push attack or nuke attack which is rated with the highest score or lowest score on the target items. Few pay attention to grey attack when a target item is rated with a lower or higher scores than the average score, which shows a more hidden rating behavior than push or nuke attack. In this paper, we present a novel detection method to make recommender systems resistant to such attacks. To characterize grey ratings, we exploit rating deviation of item to discriminate between grey attack profiles and genuine profiles. In addition, we also employ novelty and popularity of item to construct rating series. Since it is difficult to discriminate between the rating series of attacker and genuine users, we incorporate into discrete wavelet transform (DWT) to amplify these differences based on the rating series of rating deviation, novelty and popularity, respectively. Finally, we respectively extract features from rating series of rating deviation-based, novelty-based and popularity-based by using amplitude domain analysis method and combine all clustered results as our detection results. We conduct a list of experiments on the Book-Crossing dataset in diverse attack models. Experimental results were included to validate the effectiveness of our approach in comparison with benchmarked methods.

Research and education in machine learning requires diverse, representative, and open datasets that contain sufficient samples to handle the necessary training, validation, and testing tasks. Currently, the Recommender Systems area includes a large number of subfields in which accuracy and beyond-accuracy quality measures are continuously being improved. To feed this research variety, it is both necessary and convenient to reinforce the existing datasets with synthetic ones. This paper proposes a Generative Adversarial Network (GAN)-based method to generate collaborative filtering datasets in a parameterized way by selecting their preferred number of users, items, samples, and stochastic variability. This parameterization cannot be performed using regular GANs. Our GAN model is fed with dense, short, and continuous embedding representations of items and users, instead of sparse, large, and discrete vectors, to ensure fast and accurate learning, as compared to the traditional approach based on large and sparse input vectors. The proposed architecture includes a DeepMF model to extract the dense user and item embeddings and a clustering process to convert the dense GAN generated samples to the discrete and sparse samples necessary to create each required synthetic dataset. The results from three different source datasets show adequate distributions and expected quality values and evolutions in the generated datasets compared to the source datasets. Synthetic datasets and source codes are available to researchers.

The incorporation of collaborative filtering recommendation algorithms into blended teaching approaches for college English marks a big step forward in language education. This study investigates the theoretical underpinnings, practical ramifications, and pedagogical issues for adding collaborative filtering algorithms into blended learning environments. Collaborative filtering algorithms produce individualized learning resource recommendations based on user interactions and preferences, increasing student engagement and motivation. However, issues like as data privacy, algorithmic biases, and user approval must be addressed to ensure that collaborative filtering is implemented effectively in the classroom. This study explains the potential of collaborative filtering recommendation algorithms to improve language learning results in college English courses by doing a thorough literature review. It also provides ideas for educators and policymakers on how to handle the complexity of incorporating collaborative filtering recommendation algorithms into blended learning models. Finally, this paper adds to the promotion of novel pedagogical approaches and the improvement of language learning experiences among college students. As a result, the enhanced collaborative filtering recommendation system had a slightly greater recall rate and precision than the pre-optimized method.

Recommender systems have become indispensable tools in various domains, such as e-commerce, entertainment, and social media, for delivering personalized user experiences. Collaborative Filtering (CF) is an essential technique in RS that leverages user similarity patterns to suggest items which align with individual preferences. This study presents an experimental comparative analysis of collaborative filtering-based recommender system methods including memory-based methods (KNN variants), model-based approaches (SVD, SVD++, co-clustering), and techniques based on neural networks (NCF, DeepFM, LightGCN). We conduct a thorough evaluation of these methods on the MovieLens benchmark datasets (100K, 1M, 25M) utilizing various metrics, such as RMSE, MAE, FCP, NDCG@10, Precision@10, Recall@10, and F1@10 Score, aiming to identify the most effective approaches and understand the advantages and disadvantages of each approach. Additionally, we provide detailed insights into the working mechanisms of each model. Our comprehensive analysis reveals the strengths and limitations of each method, offering critical insights for practitioners in selecting the most suitable recommender system technique based on specific requirements and constraints. The findings indicate that, on large datasets, neural and graph-based models achieve measurable improvements in both rating accuracy and top-k ranking tasks, with ranking gains observed upto 15%. Nonetheless, more straightforward approaches (KNN, SVD) continue to hold their ground in smaller datasets or low-resource environments because of their straightforward implementation and clarity in interpretation. The results highlight the importance of achieving a balance between computational expense, scalability, and model intricacy when choosing collaborative filtering techniques for practical implementations of recommender systems. We offer practical insights to assist professionals in selecting models that are suited to particular application needs and data attributes. This research enhances the understanding of collaborative filtering techniques and offers valuable insights for improving the performance of RS across diverse domains.

Collaborative filtering recommendation system is a widely used method of providing recommendations using explicit ratings on items from users, which provides personalized recommendations on products or services to customers. However, the current research on recommendation has paid little attention to the use of time-related data in the recommendation process and the study on collaborative filtering to reflect changes in user interest. This paper proposed a methodology for mining a userpsilas time interest change in order to improve the performance of collaborative filtering recommender algorithms. The methodology consists of four phases of calculating time weight for the ratings, improving Pearsonpsilas correlation, forming neighbors, and recommendations. Empirical results show our time-incorporated collaborative filtering recommender system is significantly more accurate than a pure collaborative filtering system.

Recommendation system development for fashion retail e-commerce

Recommender systems are widely used in online business to satisfy user personalization demands. The most successful technique of such systems is collaborative filtering, which utilizes users' known preference to generate predictions of the unknown preferences. A key challenge for collaborative filtering recommender systems is providing high quality recommendations to new users that have not enough known preferences. In this paper, we propose a hybrid algorithm by using both the ratings and content information to tackle user-side cold-start problem. We first cluster users based on their interests and then utilize the clustering results and users' demographic information to build a decision tree to associate the novel users with the existing ones. Considering the novel user's ratings constantly increasing, we make predictions for novel users by combining our method with the collaborative filtering algorithm. Experiments on real data set show the improvement of our approach in overcoming the user-side cold-start problem.