Structural Balance Theory based Recommendation System

International Journal of e-Education, e-Business, e-Management and e-Learning, 2014

Recommender Systems (RSs) are used by an ever-increasing number of e-commerce sites to recommend items of interest to the users based on their preferences. Collaborative filtering is one of the most regularly used techniques in RSs that help the users to catch the items of interest from a massive numbers of available items. This technique is based on the idea that a set of like-mind users can help each other to find valuable information. The major challenge in recommender systems is that the user ratings or grades are very often uncertain or vague because it is based on user's tastes, opinions, and perceptions. Fuzzy sets appear to be a proper paradigm to handle the uncertainty and fuzziness of human decision making activities and to successfully model the normal sophistication of human behavior. Because of these motives, this paper adopts type-2 fuzzy linguistic approach to efficiently describe the user ratings and weights to precisely rank the relevant items to a user. The proposed method permits users to express their ratings in qualitative form, converts such preferences to their corresponding quantitative form using the concept of type-2 fuzzy logic, maps the values that represent the preferences with the retrieved items from the database, and finally recommends products that best satisfy the consumer's likings. Empirical evaluations show that the proposed technique is feasible and effective.

Social persuade plays vital part in the product marketing. Though, it's seldom been regarded in traditional Recommender systems (RS). This paper provides new paradigm RS which can exploit data in the social networks, with general approval of items, user preferences, and persuade from the social friends. The probabilistic representation is improved to build personalized recommendations like data. In world e-marketing, new commerce representations are normally introduced, new tendency started to materialize. Latest trend is the social networking websites, several of which concerned not only huge number of visitors and users, however online advertise company to put their ads on sites. This paper discovers online social networking like new e-marketing trend. We first inspect online social network like new web-based services, also evaluate social networks by other delegate web-based service. We extort information from real online social network, also our investigation of this huge dataset expose that friends contain tendency to choose similar items and provide similar ratings. The experimental outcome on the dataset illustrates that proposed scheme not only progress prediction accuracy RS but gives solution cold-start and data sparsity problems intrinsic in the collaborative filtering. Moreover, we recommend improving system performance by concern social networks semantic filtering, and authenticate its improvement through class project research. In this research we reveal how related friends may be choose for deduction based on the semantics friend relations and finer-grained customer ratings. Such technologies may be organized by mainly content providers.

International Journal of Engineering Research and Technology (IJERT), 2021

https://www.ijert.org/an-advance-recommendation-system-formulated-on-end-user-interest-and-rating-difference https://www.ijert.org/research/an-advance-recommendation-system-formulated-on-end-user-interest-and-rating-difference-IJERTV10IS040153.pdf In recent years, recommendation systems have grown in popularity and are now used in a variety of fields, including books, news, movies, research papers, search requests, social tags and business items. When it comes to creating intelligent recommendation systems that can be trained to provide better recommendations, collaborative filtering is most widely used algorithm. Currently, collaborative filtering has been profitably utilized in personalized recommendation systems. It is used by most websites, including Amazon Prime, YouTube, Netflix and Hotstar, as part of their advanced recommendation section. This method is used to provide users with recommendations based on the preferences and dislikes of other users. However, under the stipulation of extremely sparse rating data, the traditional scheme of similarity among users is relatively straightforward. Moreover, it does not consider the end-user's interest which results in pitiable performance. Due to invariability in score differences, the accuracy of the recommendation systems is hampered. So, here a system is proposed to improve the performance of the traditional collaborative filtering algorithm by considering both end-user interest and score difference.

Journal of Computer and System Sciences

Although Collaborative Filtering (CF) -based recommender systems have received great success in a variety of applications, they still under-perform and are unable to provide accurate recommendations when users and items have few ratings, resulting in reduced coverage. To overcome these limitations, we propose an effective hybrid user-item trust-based (HUIT) recommendation approach in this paper that fuses the users' and items' implicit trust information. We have also considered and computed user and item global reputations into this approach. This approach allows the recommender system to make an increased number of accurate predictions, especially in circumstances where users and items have few ratings. Experiments on four real-world datasets, particularly a business-to-business (B2B) case study, show that the proposed HUIT recommendation approach significantly outperforms state-of-the-art recommendation algorithms in terms of recommendation accuracy and coverage, as well a...

arXiv preprint arXiv:1109.4257, 2011

Abstract: This paper proposes a number of explicit and implicit ratings in product recommendation system for Business-to-customer e-commerce purposes. The system recommends the products to a new user. It depends on the purchase pattern of previous users whose purchase pattern is close to that of a user who asks for a recommendation. The system is based on weighted cosine similarity measure to find out the closest user profile among the profiles of all users in database. It also implements Association rule mining rule ...

International Journal of Engineering Applied Sciences and Technology, 2020

Recommender Engine is a specific type of smart system that uses old user feedback on products and/or additional information to make useful product recommendations. This assumes a key job in a wide scope of utilization, including web-based shopping, e-business administrations, and social ecommerce networking. Collaborative sifting (CF) is the most well-known methodologies utilized for suggestion frameworks; however, CF experiences full cold start (CCS) issue where no appraising record is accessible and with Incomplete Cold Start (ICS) issues where there are just few rating records accessible for some new things or application clients. Therefore, the recommendation algorithms for collaborative filtering are useful and play a vital role in businesses to reach out to new users and promote their services and products. This paper introduces a new cooperative filtering recommendation algorithm based on dimensionality reduction called Singular Value Decomposition (SVD) used to cluster related users and reduce dimensionality. These method and concept are continuously being used and referred in order to attain an increased and enhanced accuracy over the present Netflix system. This paper is working with Netflix's prize dataset, we use the incremental SVD approach to predict movie ratings based on previous user preferences. Different experiments are conducted to see the effect of various parameters on the algorithm's performance.

IEEE Access

Collaborative filtering (CF) is the most commonly used technique for online recommendations. CF works by computing the interests of a user by gathering preferences or taste information of other users. In this technique, similar users or items are discovered by exploring the user-item rating matrix. Based on the computed similarity, a prediction is made for the unknown or new product. There are many similarity computation methods, such as the Pearson correlation coefficient (PCC), Jaccard, Mean square difference, Cosine, etc. however, the accuracy of product recommendations using these methods is not very promising. This work introduces an improved product recommendation method for collaborative filtering, which is based on the triangle similarity. However, the downside of triangle similarity is that it only considers the common ratings of users. The proposed similarity measure not only focuses on common ratings but also consider the ratings of those items that are not commonly rated from pairs of users. The obtained similarity is further complemented with the user rating preference (URP) behavior in giving rating preferences. To evaluate the accuracy, experiments are performed on the six commonly used datasets in the field of CF. Experimental results prove that the proposed similarity measure performs well as compared to the existing similarity measures. INDEX TERMS Collaborative filtering, recommender systems, triangle similarity, user preferences.

Social network analysis emerged as an important research topic in sociology decades ago, and it has also attracted scientists from various fields of study like psychology, anthropology, geography and economics. In recent years, a significant number of researches has been conducted on using social network analysis to design e-commerce recommender systems. Most of the current recommender systems are designed for B2C e-commerce websites. This paper focuses on building a recommendation algorithm for C2C e-commerce business model by considering special features of C2C e-commerce websites. In this paper, we consider users and their transactions as a network; by this mapping, link prediction technique which is an important task in social network analysis could be used to build the recommender system. The proposed tow-level recommendation algorithm, rather than topology of the network, uses nodes' features like: category of items, ratings of users, and reputation of sellers. The results show that the proposed model can be used to predict a portion of future trades between users in a C2C commercial network.

2006 10th International Database Engineering and Applications Symposium (IDEAS'06), 2006

Collaborative Filtering (CF) Systems are gaining widespread acceptance in recommender systems and ecommerce applications. These systems combine information retrieval and data mining techniques to provide recommendations for products, based on suggestions of users with similar preferences. Nearest-neighbor CF process is influenced by several factors, which were not examined carefully in past work. In this paper, we bring to surface these factors in order to identify existing false beliefs. Moreover, by being able to view the "big picture" from the CF process, we propose new approaches that substantially improve the performance of CF algorithms. For instance, we obtain more than 40% percent increase in precision in comparison to widely-used CF algorithms. We perform an extensive experimental evaluation, with several real data sets, and produce results that invalidate some existing beliefs and illustrate the superiority of the proposed extensions.