Deep Matrix Factorization With Implicit Feedback Embedding for Recommendation System

Yi, Baolin; Shen, Xiaoxuan; Liu, Hai; Zhang, Wei; Liu, Sanya; Xiong, Naixue

doi:10.1109/tii.2019.2893714

Cited by 192 publications

(57 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To build a model of our recommender system, we use the Alternating Least Squares (ALS) algorithm [41], [42], [43]. ALS is a model-based CF algorithm belonging to the class of matrix factorization (MF) algorithms [42], [44], [45], [46]. MF algorithms have become widely known since the Netflix Prize Challenge, in predicting user ratings for films [16].…”

Section: A Collaborative Filtering and Matrix Factorizationmentioning

confidence: 99%

Expanding the Number of Reviewers in Open-Source Projects by Recommending Appropriate Developers

Chueshev

Lawall

Bendraou

et al. 2020

2020 IEEE International Conference on Software Maintenance and Evolution (ICSME)

View full text Add to dashboard Cite

Code review is an important part of the development of any software project. Recently, many open source projects have begun practicing lightweight and tool-based code review (a.k.a modern code review) to make the process simpler and more efficient. However, those practices still require reviewers, of which there may not be sufficiently many to ensure timely decisions. In this paper, we propose a recommender-based approach to be used by open-source projects to increase the number of reviewers from among the appropriate developers. We first motivate our approach by an exploratory study of nine projects hosted on GitHub and Gerrit. Secondly, we build the recommender system itself, which, given a code change, initially searches for relevant reviewers based on similarities between the reviewing history and the files affected by the change, and then augments this set with developers who have a similar development history as these reviewers but have little or no relevant reviewing experience. To make these recommendations, we rely on collaborative filtering, and more precisely, on matrix factorization. Our evaluation shows that all nine projects could benefit from our system by using it both to get recommendations of previous reviewers and to expand their number from among the appropriate developers.

show abstract

Section: A Collaborative Filtering and Matrix Factorizationmentioning

confidence: 99%

Expanding the Number of Reviewers in Open-Source Projects by Recommending Appropriate Developers

Chueshev

Lawall

Bendraou

et al. 2020

2020 IEEE International Conference on Software Maintenance and Evolution (ICSME)

View full text Add to dashboard Cite

show abstract

“…Matrix Factorization methods have confirmed a higher performance in data and image processing, however they have associated a greater computational complexity [41], a hybrid fusion collaborative recommendation solution maximizes feature engineering with feed forward neural networks to associate customer and product relationship into a dimensional feature space where product-customer similarity and the preferred products is optimized; Tensor Factorization (TF) improves generalization representing a multi-view data from customers that follow their purchasing and rating history. An improved recommendation model based on item-diversity adds customer interests and implicit feedback [42], it is based on the variance to the matrix factorization algorithm. A collaborative filtering application based on a deep learning method with a deep matrix factorization integrates any type of data and information [43]; two functions that transform features are incorporated to produce latent features of customers and products from diverse input data, in addition, an implicit feedback embedding transforms the implicit sparse and high-dimensional feedback data into a low dimension and real value vector that retains its primary factors.…”

Section: Recommender Systems For Big Datamentioning

confidence: 99%

Intelligent Recommender System for Big Data Applications Based on the Random Neural Network

Serrano¹

2019

BDCC

View full text Add to dashboard Cite

Online market places make their profit based on their advertisements or sales commission while businesses have the commercial interest to rank higher on recommendations to attract more customers. Web users cannot be guaranteed that the products provided by recommender systems within Big Data are either exhaustive or relevant to their needs. This article analyses the product rank relevance provided by different commercial Big Data recommender systems (Grouplens film, Trip Advisor and Amazon); it also proposes an Intelligent Recommender System (IRS) based on the Random Neural Network; IRS acts as an interface between the customer and the different Recommender Systems that iteratively adapts to the perceived user relevance. In addition, a relevance metric that combines both relevance and rank is presented; this metric is used to validate and compare the performance of the proposed algorithm. On average, IRS outperforms the Big Data recommender systems after learning iteratively from its customer.

show abstract

“…With the development of information technology, the data on the Internet has grown exponentially, and how to effectively provide relevant information to users in need is facing great challenges [1][2][3][4] in recent years. To this end, various information sharing systems have been spawned, and online social networks are undoubtedly one of the most popular Internet products in the last decade [5][6][7], which provides the basic conditions for maintaining social relationships, such as discovering users with similar interests and hobbies, and acquiring information and knowledge shared by other users.…”

Section: Introductionmentioning

confidence: 99%

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

et al. 2020

View full text Add to dashboard Cite

The recommendation system is an effective means to solve the information overload problem that exists in social networks, which is also one of the most common applications of big data technology. Thus, the matrix decomposition recommendation model based on scoring data has been extensively studied and applied in recent years, but the data sparsity problem affects the recommendation quality of the model. To this end, this paper proposes a hybrid recommendation model based on deep emotion analysis and multi-source view fusion which makes a personalized recommendation with user-post interaction ratings, implicit feedback and auxiliary information in a hybrid recommendation system. Specifically, the HITS algorithm is used to process the data set, which can filter out the users and posts with high influence and eliminate most of the low-quality users and posts. Secondly, the calculation method of measuring the similarity of candidate posts and the method of calculating K nearest neighbors are designed, which solves the problem that the text description information of post content in the recommendation system is difficult to mine and utilize. Then, the cooperative training strategy is used to achieve the fusion of two recommended views, which eliminates the data distribution deviation added to the training data pool in the iterative training. Finally, the performance of the DMHR algorithm proposed in this paper is compared with other state-of-art algorithms based on the Twitter dataset. The experimental results show that the DMHR algorithm has significant improvements in score prediction and recommendation performance.

show abstract

Deep Matrix Factorization With Implicit Feedback Embedding for Recommendation System

Cited by 192 publications

References 32 publications

Expanding the Number of Reviewers in Open-Source Projects by Recommending Appropriate Developers

Expanding the Number of Reviewers in Open-Source Projects by Recommending Appropriate Developers

Intelligent Recommender System for Big Data Applications Based on the Random Neural Network

A hybrid recommendation model in social media based on deep emotion analysis and multi-source view fusion

Contact Info

Product

Resources

About