A New Similarity Computation Method in Collaborative Filtering Based Recommendation System

2017 ◽  
Author(s):  
Xiaokun Wu ◽  
Yongfeng Huang ◽  
Shihui Wang
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
Computation Method ◽  
Similarity Computation

Similarity Computation Method for Collaborative Filtering Based on Optimization

2010 ◽  
Vol 14 (6) ◽  
pp. 654-660
Author(s):  
Akihiro Yamashita ◽  
◽  
Hidenori Kawamura ◽  
Keiji Suzuki
Keyword(s):  
Collaborative Filtering ◽  
Correlation Coefficient ◽  
Optimal Solution ◽  
Computation Method ◽  
Pearson’S Correlation ◽  
Pearson’S Correlation Coefficient ◽  
Active User ◽  
Pearson's Correlation ◽  
Similarity Computation ◽  
Pearson's Correlation Coefficient

The recommender system provides personalized recommendations at many e-commerce websites. Collaborative filtering is one of the most popular and effective recommendation algorithms. User-based collaborative filtering, the conventional approach in collaborative filtering, uses user similarity computed based on user item rating. Recommendations are provided by calculating rating predictions based on similarity. Pearson’s correlation coefficient or cosign distance is used as similarity. Until now, a lot of discussions for efficient similarity computation were given by many researchers. Despite active discussion of similarity computation, little computation has been made for optimal similarity in collaborative filtering. In this research, similarity optimization problem was formulated by defining similarities between an active user and other users as a vector variable. The quasi-optimal solution was obtained based on Particle Swarm Optimization (PSO) approach, compared to Pearson’s correlation coefficient. Experimental results based on agentbased simulation and sample dataset show that similarity based on PSO improves recommendation accuracy. We also found that PSO-based similarity computation provides rating predictions for unknown ratings more accurately than conventional similarity computation.

scholarly journals Discretization Based Framework to Improve the Recommendation Quality

2021 ◽  
Vol 18 (3) ◽  
Author(s):  
Bilal Ahmed ◽  
Wang Li
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
Information Filtering ◽  
Nearest Neighbors ◽  
User Preferences ◽  
Primary Concern ◽  
K Nearest Neighbors ◽  
Chi Square ◽  
Similarity Computation ◽  
Rating Prediction

Recommendation systems are information filtering software that delivers suggestions about relevant stuff from a massive collection of data. Collaborative filtering approaches are the most popular in recommendations. The primary concern of any recommender system is to provide favorable recommendations based on the rating prediction of user preferences. In this article, we propose a novel discretization based framework for collaborative filtering to improve rating prediction. Our framework includes discretization-based preprocessing, chi-square based attribution selection, and K-Nearest Neighbors (KNN) based similarity computation. Rating prediction affords some basis for the judgment to decide whether recommendations are generated or not, subject to the ratio of performance of any recommendation system. Experiments on two datasets MovieLens and BookCrossing, demonstrate the effectiveness of our method.

Identifying Attack Models for Securing Cluster-Based Recommendation System

2020 ◽  
Vol 14 ◽  
Author(s):  
Amreen Ahmad ◽  
Tanvir Ahmad ◽  
Ishita Tripathi
Keyword(s):  
Collaborative Filtering ◽  
Recommender System ◽  
Recommendation System ◽  
Relevant Information ◽  
System Function ◽  
Recommendation Algorithm ◽  
Underlying Network ◽  
Entire Dataset ◽  
Attack Models ◽  
Wide Usage

: The immense growth of information has led to the wide usage of recommender systems for retrieving relevant information. One of the widely used methods for recommendation is collaborative filtering. However, such methods suffer from two problems, scalability and sparsity. In the proposed research, the two issues of collaborative filtering are addressed and a cluster-based recommender system is proposed. For the identification of potential clusters from the underlying network, Shapley value concept is used, which divides users into different clusters. After that, the recommendation algorithm is performed in every respective cluster. The proposed system recommends an item to a specific user based on the ratings of the item’s different attributes. Thus, it reduces the running time of the overall algorithm, since it avoids the overhead of computation involved when the algorithm is executed over the entire dataset. Besides, the security of the recommender system is one of the major concerns nowadays. Attackers can come in the form of ordinary users and introduce bias in the system to force the system function that is advantageous for them. In this paper, we identify different attack models that could hamper the security of the proposed cluster-based recommender system. The efficiency of the proposed research is validated by conducting experiments on student dataset.

scholarly journals Extrapolative Collaborative Filtering Recommendation System with Word2Vec for Purchased Product for SMEs

2021 ◽  
Vol 13 (13) ◽  
pp. 7156
Author(s):  
Kyoung Jun Lee ◽  
Yu Jeong Hwangbo ◽  
Baek Jeong ◽  
Ji Woong Yoo ◽  
Kyung Yang Park
Keyword(s):  
Collaborative Filtering ◽  
High Performance ◽  
Recommendation System ◽  
Small And Medium Enterprises ◽  
Personal Information ◽  
Business Environment ◽  
Share Data ◽  
Artificial Intelligence Technology ◽  
Medium Enterprises ◽  
Start Ups

Many small and medium enterprises (SMEs) want to introduce recommendation services to boost sales, but they need to have sufficient amounts of data to introduce these recommendation services. This study proposes an extrapolative collaborative filtering (ECF) system that does not directly share data among SMEs but improves recommendation performance for small and medium-sized companies that lack data through the extrapolation of data, which can provide a magical experience to users. Previously, recommendations were made utilizing only data generated by the merchant itself, so it was impossible to recommend goods to new users. However, our ECF system provides appropriate recommendations to new users as well as existing users based on privacy-preserved payment transaction data. To accomplish this, PP2Vec using Word2Vec was developed by utilizing purchase information only, excluding personal information from payment company data. We then compared the performances of single-merchant models and multi-merchant models. For the merchants with more data than SMEs, the performance of the single-merchant model was higher, while for the SME merchants with fewer data, the multi-merchant model’s performance was higher. The ECF System proposed in this study is more suitable for the real-world business environment because it does not directly share data among companies. Our study shows that AI (artificial intelligence) technology can contribute to the sustainability and viability of economic systems by providing high-performance recommendation capability, especially for small and medium-sized enterprises and start-ups.

scholarly journals A Collaborative Filtering Algorithm with Intragroup Divergence for POI Group Recommendation

2021 ◽  
Vol 11 (12) ◽  
pp. 5416
Author(s):  
Yanheng Liu ◽  
Minghao Yin ◽  
Xu Zhou
Keyword(s):  
Collaborative Filtering ◽  
User Preference ◽  
Computation Method ◽  
Group Recommendation ◽  
Preference Rating ◽  
Filtering Method ◽  
Personal Recommendation ◽  
Collaborative Filtering Algorithm ◽  
Group Members ◽  
Individual Recommendation

The purpose of POI group recommendation is to generate a recommendation list of locations for a group of users. Most of the current studies first conduct personal recommendation and then use recommendation strategies to integrate individual recommendation results. Few studies consider the divergence of groups. To improve the precision of recommendations, we propose a POI group recommendation method based on collaborative filtering with intragroup divergence in this paper. Firstly, user preference vector is constructed based on the preference of the user on time and category. Furthermore, a computation method similar to TF-IDF is presented to compute the degree of preference of the user to the category. Secondly, we establish a group feature preference model, and the similarity of the group and other users’ feature preference is obtained based on the check-ins. Thirdly, the intragroup divergence of POIs is measured according to the POI preference of group members and their friends. Finally, the preference rating of the group for each location is calculated based on a collaborative filtering method and intragroup divergence computation, and the top-ranked score of locations are the recommendation results for the group. Experiments have been conducted on two LBSN datasets, and the experimental results on precision and recall show that the performance of the proposed method is superior to other methods.

scholarly journals User profile correlation-based similarity (UPCSim) algorithm in movie recommendation system

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Triyanna Widiyaningtyas ◽  
Indriana Hidayah ◽  
Teguh B. Adji
Keyword(s):  
Collaborative Filtering ◽  
Recommendation System ◽  
User Behavior ◽  
Correlation Coefficients ◽  
User Profile ◽  
Profile Data ◽  
Similarity Algorithm ◽  
Previous Algorithm ◽  
Movie Recommendation ◽  
Recommendation Accuracy

AbstractCollaborative filtering is one of the most widely used recommendation system approaches. One issue in collaborative filtering is how to use a similarity algorithm to increase the accuracy of the recommendation system. Most recently, a similarity algorithm that combines the user rating value and the user behavior value has been proposed. The user behavior value is obtained from the user score probability in assessing the genre data. The problem with the algorithm is it only considers genre data for capturing user behavior value. Therefore, this study proposes a new similarity algorithm – so-called User Profile Correlation-based Similarity (UPCSim) – that examines the genre data and the user profile data, namely age, gender, occupation, and location. All the user profile data are used to find the weights of the similarities of user rating value and user behavior value. The weights of both similarities are obtained by calculating the correlation coefficients between the user profile data and the user rating or behavior values. An experiment shows that the UPCSim algorithm outperforms the previous algorithm on recommendation accuracy, reducing MAE by 1.64% and RMSE by 1.4%.

Sign in / Sign up

Export Citation Format

Share Document