The YouTube video recommendation system

Davidson, James; Liebald, Benjamin; Liu, Junning; Nandy, Palash; Vleet, Taylor Van; Gargi, Ullas; Gupta, S. K.; He, Yu; Lambert, M. L.; Livingston, Blake; Sampath, Dasarathi

doi:10.1145/1864708.1864770

Cited by 986 publications

(539 citation statements)

References 5 publications

Supporting

Mentioning

519

Contrasting

Unclassified

Order By: Relevance

“…Online shops, like Amazon [14], internet radios, like Last.FM [4], and video sharing website, like YouTube [6] apply recommendation techniques to personalize their website according to the needs of each user. Purchasing, clicking and rating behaviour are valuable information channels for online retailers and content providers to investigate consumers' interests and generate personalized recommendations [13].…”

Section: Related Workmentioning

confidence: 99%

Extending User Profiles in Collaborative Filtering Algorithms to Alleviate the Sparsity Problem

Pessemier

Vanhecke

Dooms

et al. 2011

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

Abstract. The overabundance of information and the related difficulty to discover interesting content has complicated the selection process for end-users. Recommender systems try to assist in this content-selection process by using intelligent personalisation techniques which filter the information. Most commonly-used recommendation algorithms are based on Collaborative Filtering (CF). However, present-day CF techniques are optimized for suggesting provider-generated content and partially lose their effectiveness when recommending user-generated content. Therefore, we propose an advanced CF algorithm which considers the specific characteristics of user-generated content (like the sparsity of the data matrix). To alleviate this sparsity problem, profiles are extended with probable future consumptions. These extended profiles increase the profile overlap probability, thereby increasing the number of neighbours used for calculating the recommendations. This way, the recommendations become more precise and diverse compared to traditional CF recommendations. This paper explains the proposed algorithm in detail and demonstrates the improvements on standard CF.

show abstract

Section: Related Workmentioning

confidence: 99%

Extending User Profiles in Collaborative Filtering Algorithms to Alleviate the Sparsity Problem

Pessemier

Vanhecke

Dooms

et al. 2011

Lecture Notes in Business Information Processing

View full text Add to dashboard Cite

show abstract

“…At present, the recommender systems have become the main way to help users filter large amounts of information, which aims to help them to choose item, thus alleviating the problem of information overload. There are many recommender systems have been put forward and practical applications, such as Amazon [1], YouTube [2], Netflix [3] and so on.…”

Section: Introductionmentioning

confidence: 99%

A New Approach for Improving Collaborative filtering Recommender Systems

Tang¹,

Jin²

2017

Proceedings of the 2017 International Conference on Material Science, Energy and Environmental Engineering (MSEEE 2017)

View full text Add to dashboard Cite

Abstract. Nowadays, collaborative filtering (CF) is the most widely used method for proving recommendations in online environments, which is designed to filter large amounts of information in order to recommend to the user what they may be interested in. The user-based CF calculates the similarity between users by comparing the ratings of users to the common item, the rating generated at different times are weighted equally, but the effect of time on the user is not considered. In this paper, we propose a dynamic multi-level and time-weighted (DMLTW) collaborative filtering recommendation algorithm. Based on the original time-weighted, a new user-based time-weighted function is proposed, considering the influence of time factor on the recommendation result. At the same time, we present a positive and negative adjustment method to divide the user's similarity into different levels so as to achieve better recommendation quality. Experimental results show that our proposed method improves the accuracy of the user-based recommender systems and has a lower MAE compared to the reference method.

show abstract

“…It helps users handle information explosion problem and obtain their own meaningful information, services, and recommendations more conveniently and quickly. Some examples would be Amazon and YouTube [4], [6]. For given users, items and ratings, recommender systems attempt to forecast ratings of the unseen items or generate a list of items (movies, music, news, others) that may interest users.…”

Section: Introductionmentioning

confidence: 99%

A Collaborative Filtering Recommendation Algorithm Based on Hierarchical Structure and Time Awareness

Guo

Tang

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYUser-based and item-based collaborative filtering (CF) are two of the most important and popular techniques in recommender systems. Although they are widely used, there are still some limitations, such as not being well adapted to the sparsity of data sets, failure to consider the hierarchical structure of the items, and changes in users' interests when calculating the similarity of items. To overcome these shortcomings, we propose an evolutionary approach based on hierarchical structure for dynamic recommendation system named Hierarchical Temporal Collaborative Filtering (HTCF). The main contribution of the paper is displayed in the following two aspects. One is the exploration of hierarchical structure between items to improve similarity, and the other is the improvement of the prediction accuracy by utilizing a time weight function. A unique feature of our method is that it selects neighbors mainly based on hierarchical structure between items, which is more reliable than co-rated items utilized in traditional CF. To the best of our knowledge, there is little previous work on researching CF algorithm by combining object implicit or latent object-structure relations. The experimental results show that our method outperforms several current recommendation algorithms on recommendation accuracy (in terms of MAE).

show abstract

The YouTube video recommendation system

Cited by 986 publications

References 5 publications

Extending User Profiles in Collaborative Filtering Algorithms to Alleviate the Sparsity Problem

Extending User Profiles in Collaborative Filtering Algorithms to Alleviate the Sparsity Problem

A New Approach for Improving Collaborative filtering Recommender Systems

A Collaborative Filtering Recommendation Algorithm Based on Hierarchical Structure and Time Awareness

Contact Info

Product

Resources

About