A dynamic multi-level collaborative filtering method for improved recommendations

Polatidis, Nikolaos; Georgiadis, Christos K.

doi:10.1016/j.csi.2016.10.014

Cited by 47 publications

(22 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Jesús et al [12] proposed a similarity calculating method based on singular points to extract the contextual user information and calculate the singularity of each item. To increase the accuracy of recommendation, Polatidis et al [13] improved the CF algorithm by taking the number of items rated jointly by users and the value of Pearson similarity as constraints and adjusted the user similarity according to the corresponding threshold value. Tao et al [14] divided the dimensions of items into different types and calculated the average preference of all users for these dimensions.…”

Section: Improvement Of Similarity Calculating Methodsmentioning

confidence: 99%

Rating Prediction Algorithm Based on User Time-Sensitivity

Cheng

Wang

2019

Information

View full text Add to dashboard Cite

Rating prediction is an important technology in the personalized recommendation field. Prediction results are influenced by many factors, such as time, and their accuracy directly affects the quality of the recommendation. Current time-based collaborative filtering (CF) algorithms have improved the technology of prediction accuracy to a certain extent, but they fail to differentiate the time-sensitivity of different users, which further affects prediction accuracy. To address this issue, we have proposed a rating prediction algorithm based on user time-sensitivity differences. First, we analyzed and modeled the time sensitivities of users, utilized cosine distance and relative entropy to build a judgment function, and then judged the time sensitivities of users based on a voting strategy. Next, we applied the time-sensitivity difference to improve the traditional CF algorithm and optimized the combination of parameters. Finally, we tested our algorithm on standard datasets. The experimental results showed that there are many users who have different sensitivities to time. According to these experimental results, our proposed algorithm has achieved a higher prediction accuracy than other state-of-the-art algorithms.

show abstract

Section: Improvement Of Similarity Calculating Methodsmentioning

confidence: 99%

Rating Prediction Algorithm Based on User Time-Sensitivity

Cheng

Wang

2019

Information

View full text Add to dashboard Cite

show abstract

“…Traditional collaborative filtering recommendation algorithm uses single dimensional data to calculate the similarity between users or items, on the contrast, the MDAA recommendation algorithm is add additional rating information for original users [11][12][13][14] and consider the user's rating preferences at the same time, then increase the accuracy of recommendations.…”

Section: Mdaa Recommend Algorithmmentioning

confidence: 99%

Multi-dimensional Aggregation Recommendation Algorithm Based on Average Prediction

2018

View full text Add to dashboard Cite

Traditional collaborative filtering recommendation algorithm uses single dimensional data to calculate the similarity between users or items, ignoring the user’s preference, thus affect the recommendation accuracy. To this end, an averaging forecasting based multi-dimensional aggregation recommendation algorithm was proposed in this paper, which constructs the relationship aggregation function by user’s total score and dimension scores firstly, then apply the aggregation function to the initial multi-dimensional score that calculated by the modified averaging forecasting algorithm. The experiment result shows that compared with the previous collaborative filtering based recommendation algorithm, it has higher recommendation accuracy.

show abstract

“…With the rapid development of the Internet and the emergence of big data, information and data have exploded in size, and it is more difficult for people to obtain accurate and efficient information in time. Therefore, recommendation systems [1,2] have received more and more attention, including content-based recommendation algorithms [3,4], collaborative filtering algorithms [5][6][7], and hybrid approaches [8,9]. A good recommendation algorithm can better understand the user's purchase intention and can improve the user's viscosity for the e-commerce platform, thereby increasing the user's purchase rate.…”

Section: Introductionmentioning

confidence: 99%

A Personalized Recommendation Algorithm Based on the User’s Implicit Feedback in E-Commerce

Wang

2018

Future Internet

View full text Add to dashboard Cite

A recommendation system can recommend items of interest to users. However, due to the scarcity of user rating data and the similarity of single ratings, the accuracy of traditional collaborative filtering algorithms (CF) is limited. Compared with user rating data, the user’s behavior log is easier to obtain and contains a large amount of implicit feedback information, such as the purchase behavior, comparison behavior, and sequences of items (item-sequences). In this paper, we proposed a personalized recommendation algorithm based on a user’s implicit feedback (BUIF). BUIF considers not only the user’s purchase behavior but also the user’s comparison behavior and item-sequences. We extracted the purchase behavior, comparison behavior, and item-sequences from the user’s behavior log; calculated the user’s similarity by purchase behavior and comparison behavior; and extended word-embedding to item-embedding to obtain the item’s similarity. Based on the above method, we built a secondary reordering model to generate the recommendation results for users. The results of the experiment on the JData dataset show that our algorithm shows better improvement in regard to recommendation accuracy over other CF algorithms.

show abstract

A dynamic multi-level collaborative filtering method for improved recommendations

Cited by 47 publications

References 33 publications

Rating Prediction Algorithm Based on User Time-Sensitivity

Rating Prediction Algorithm Based on User Time-Sensitivity

Multi-dimensional Aggregation Recommendation Algorithm Based on Average Prediction

A Personalized Recommendation Algorithm Based on the User’s Implicit Feedback in E-Commerce

Contact Info

Product

Resources

About