A recommender system is an important subject in the field of data mining, where the item rating information from users is exploited and processed to make suitable recommendations with all other users. The recommender system creates convenience for e-commerce users and stimulates the consumption of items that are suitable for users. In addition to e-commerce, a recommender system is also used to provide recommendations on books to read, movies to watch, courses to take or websites to visit. Similarity between users is an important impact for recommendation, which could be calculated from the data of past user ratings of the item by methods of collaborative filtering, matrix factorization or singular vector decomposition. In the development of graph data mining techniques, the relationships between users and items can be represented by matrices from which collaborative filtering could be done with the larger database, more accurate and faster in calculation. All of these data can be represented graphically and mined by today’s highly developed graph neural network models. On the other hand, users’ social friendship data also influence consumption habits because recommendations from friends will be considered more carefully than information sources. However, combining a user’s friend influence and the similarity between users whose similar shopping habits is challenging. Because the information is noisy and its affects each particular data set in different ways. In this study, we present the input data processing method to remove outliers which are single reviews or users with little interaction with the items; the next proposed model will combine the social relationship data and the similarity in the rating history of users to improve the accuracy and recall of the recommender system. We perform a comparative assessment of the influence of each data set and calculation method on the final recommendation. We also propose and implement a model and compared it with base line models which include NGCF, LightGCN, WiGCN, SocialLGN and SEPT.

Recommender systems have undergone more than three decades of continuous development, evolving from early collaborative filtering techniques and matrix factorization to the integration of deep learning methods. In recent years, ranking prediction in collaborative filtering has attracted particular attention, as it directly impacts personalization quality in domains such as e-commerce, social media, and multimedia services. Among various approaches, Graph Neural Networks have emerged as a dominant paradigm, owing to their inherent ability to model high-order user–item relationships. This survey provides a systematic and up-to-date review of graph-based collaborative filtering models for ranking prediction, covering the period 2020–2025 and analyzing 80 representative works. We classify existing methods along multiple dimensions, including graph learning techniques, model architectures, auxiliary learning strategies, recommendation scenarios, and application domains. Furthermore, we summarize evaluation protocols and benchmark datasets to provide practical guidance for future experimentation. Finally, we discuss major challenges—such as data sparsity, cold start, oversmoothing, fairness, and scalability—and outline promising research directions, including self-supervised learning, multimodal modeling, and the integration of large language models into recommender systems. This work aims to serve both researchers and practitioners as a comprehensive reference and a roadmap for advancing the field of GNN-based ranking prediction in collaborative filtering.