Temporal Collaborative Filtering with Bayesian Probabilistic Tensor Factorization

Xiong, Liang; Chen, Xi; Huang, Tao; Schneider, Jeff; Carbonell, Jaime G.

doi:10.1137/1.9781611972801.19

Cited by 500 publications

(423 citation statements)

References 24 publications

Supporting

Mentioning

421

Contrasting

Unclassified

Order By: Relevance

“…In this work, we do not heavily tune parameters and only wish to see whether these proposed approaches work in principle. One way to deploy a "parameter-free" model might be to consider a Bayesian treatment of Latent Factor Models, like [27,29]. However, the sheer amount of data and its continuous nature prevent us to explore Bayesian treatment in this work and leave it to the future work.…”

Section: Summary and Discussionmentioning

confidence: 99%

“…Latent Factor Models (LFM) are widely used in recommender systems (e.g., [17,29,31,30]) and have proven effective in many scenarios (e.g., [17]). Specifically, LFM can model the interactions between different types of entities such as user-user and user-item, discovering their latent relationships.…”

Section: Latent Factor Modelsmentioning

confidence: 99%

“…and applied to social media as well (e.g., [24,29]). However, we do not choose the Tucker decomposition for our settings because not only it requires to pre-specify the dimensionality of all factors separately, but also does not guarantee uniqueness of the decomposition result.…”

Section: Latent Factor Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Learning to rank social update streams

Liu

Bekkerman

Adler

et al. 2012

Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

As online social media further integrates deeper into our lives, we spend more time consuming social update streams that come from our online connections. Although social update streams provide a tremendous opportunity for us to access information on-the-fly, we often complain about its relevance. Some of us are flooded with a steady stream of information and simply cannot process it in full. Ranking the incoming content becomes the only solution for the overwhelmed users. For some others, in contrast, the incoming information stream is pretty weak, and they have to actively search for relevant information which is quite tedious. For these users, augmenting their incoming content flow with relevant information from outside their first-degree network would be a viable solution. In that case, the problem of relevance becomes even more prominent.In this paper, we start an open discussion on how to build effective systems for ranking social updates from a unique perspective of LinkedIn -the largest professional network in the world. More specifically, we address this problem as an intersection of learning to rank, collaborative filtering, and clickthrough modeling, while leveraging ideas from information retrieval and recommender systems. We propose a novel probabilistic latent factor model with regressions on explicit features and compare it with a number of non-trivial baselines. In addition to demonstrating superior performance of our model, we shed some light on the nature of social updates on LinkedIn and how users interact with them, which might be applicable to social update streams in general.

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

Section: Latent Factor Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Learning to rank social update streams

Liu

Bekkerman

Adler

et al. 2012

Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…The benefits of such methods are that they can treat a large set of customer and product data to seek hidden patterns in reduced-dimensional space. Tensor factorization [25,39] can decompose a data cube of a large set of customers, products and time periods to a scalable low-rank matrix to find hidden patterns related to customer behavior. However, such studies cannot address a marketing variable structure explicitly like marketing models.…”

Section: Dimension Reduction Methodsmentioning

confidence: 99%

Personalized market response analysis for a wide variety of products from sparse transaction data

Ishigaki

Terui

Sato

et al. 2018

Int J Data Sci Anal

View full text Add to dashboard Cite

Advanced database marketing is designed to ascertain individual customers' market responses with a discount or display of widely various products from transaction data. However, transaction data recorded in a supermarket or electric commerce are fundamentally sparse because most customers purchase only a few products from all products in shops. Existing methods are not applicable to elucidate the personalized response because of a lack of sample size of purchased data. This paper proposes a personalized market response estimation method for a wide set of customers and products from these sparse data. The method compresses a sparse transaction data with information related to response to marketing variables into a reduced-dimensional space for feasible parameter estimation. Then, they are decompressed into original space using augmented latent variables to obtain individual response parameters. Results show that the method can find suitable marketing promotions for individual customers to every analyzed product.

show abstract

“…Matrix completion Matrix factorization methods are studied extensively for collaborative filtering [23,16,28,29,40]. Whereas the standard recommender problem can be treated in 2D (items vs. users), our problem has an inherent 3D structure; we account for it using a tensor factorization approach originally developed to model movie ratings as trends vary over time [40].…”

Section: Synthetic Datamentioning

confidence: 99%