Coupled Matrix Factorization Within Non-IID Context

Li, Fangfang; Xu, Guandong; Cao, Longbing

doi:10.1007/978-3-319-18032-8_55

Cited by 15 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In complex applications such as stock analysis, there usually exists coupling effects between different features. To capture such effects, inspired by the previous works [43,44], we apply a Coupled Stock Similarity (CSS) measure by taking the intra interaction between values within an attribute and the inter interaction between attributes into account to calculate the correlation between stocks. In this work, the coupling attributes of stocks include the closing price and the industry index trend in each trading day, which are both crucial attributes for a stock, and empirically have coupling effects.…”

Section: Building the Stock Correlation Matrixmentioning

confidence: 99%

Improving stock market prediction via heterogeneous information fusion

Zhang

Wang

et al. 2018

Knowledge-Based Systems

149

View full text Add to dashboard Cite

Traditional stock market prediction approaches commonly utilize the historical price-related data of the stocks to forecast their future trends. As the Web information grows, recently some works try to explore financial news to improve the prediction. Effective indicators, e.g., the events related to the stocks and the people's sentiments towards the market and stocks, have been proved to play important roles in the stocks' volatility, and are extracted to feed into the prediction models for improving the prediction accuracy. However, a major limitation of previous methods is that the indicators are obtained from only a single source whose reliability might be low, or from several data sources but their interactions and correlations among the multi-sourced data are largely ignored.In this work, we extract the events from Web news and the users' sentiments from social media, and investigate their joint impacts on the stock price movements via a coupled matrix and tensor factorization framework. Specifically, a tensor is firstly constructed to fuse heterogeneous data and capture the intrinsic * Corresponding author relations among the events and the investors' sentiments. Due to the sparsity of the tensor, two auxiliary matrices, the stock quantitative feature matrix and the stock correlation matrix, are constructed and incorporated to assist the tensor decomposition. The intuition behind is that stocks that are highly correlated with each other tend to be affected by the same event. Thus, instead of conducting each stock prediction task separately and independently, we predict multiple correlated stocks simultaneously through their commonalities, which are enabled via sharing the collaboratively factorized low rank matrices between matrices and the tensor. Evaluations on the China A-share stock data and the HK stock data in the year 2015 demonstrate the effectiveness of the proposed model.

show abstract

Section: Building the Stock Correlation Matrixmentioning

confidence: 99%

Improving stock market prediction via heterogeneous information fusion

Zhang

Wang

et al. 2018

Knowledge-Based Systems

149

View full text Add to dashboard Cite

show abstract

“…Coupled matrix factorization is an approach that performs a joint factorization of two or more matrices. Several attempts have been made to develop different variants of coupled matrix factorization methods in [10], [11] and [12]. However, our methods are the first and only context-aware coupled matrix factorization as far as we can tell.…”

Section: B Coupled Matrix Factorizationmentioning

confidence: 99%

“…"Coupling" according to [12] and [11] means the relationship among attributes of items in a dataset. They created a coupled similarity method that measures the similarity between attributes and characteristics of items to identify the relationship in the dataset.…”

Section: B Coupled Matrix Factorizationmentioning

confidence: 99%

See 1 more Smart Citation

Context-Aware Recommendation Methods

Agagu¹,

Tran²

2018

IJISA

View full text Add to dashboard Cite

A context-aware recommender system attempts to generate better recommendations using contextual information. However, generating recommendations for specific contexts have been challenging because of the difficulties in using contextual information to enhance the capabilities of recommender systems. Several methods have been used to incorporate contextual information into traditional recommendation algorithms and data modeling techniques. These methods focus on incorporating contextual information to improve general recommendations for users rather than identifying the different context applicable to the user and providing recommendations geared towards those specific contexts. We develop two methods: the first method attaches user preference across multiple contextual conditions, assuming that user preference remains the same, but the suitability of items differs across different contextual conditions. The second method assumes that item suitability remains the same across different contextual conditions but user preference changes. We perform some experiments on the last.fm dataset to evaluate our methods. We also compared our work to other context-aware recommendation approaches. Our results show that grouping ratings by context and jointly factorizing with common factors improves prediction accuracy.

show abstract

“…They proposed the non-IID recommendation theories and systems [6]. Considering the non-IID context, Li et al [16] presented a coupled matrix factorization framework, which integrated user couplings and item couplings into the basic matrix factorization model.…”

Section: Related Workmentioning

confidence: 99%

Recommendation in heterogeneous information network via dual similarity regularization

Zheng

Liu

Shi

et al. 2016

Int J Data Sci Anal

View full text Add to dashboard Cite

Recommender system has caught much attention from multiple disciplines, and many techniques are proposed to build it. Recently, social recommendation becomes a hot research direction. The social recommendation methods tend to leverage social relations among users obtained from social network to alleviate data sparsity and cold-start problems in recommender systems. It employs simple similarity information of users as social regularization on users. Unfortunately, the widely used social regularization suffers from several aspects: (1) The similarity information of users only stems from social relations of related users; (2) it only has constraint on users without considering the impact of items for recommendation; (3) it may not work well for dissimilar users. To overcome the shortcomings of social regularization, we design a novel dual similarity regularization to impose the constraint on users and items with high and low similarities simultaneously. With the dual similarity regularization, we further propose an optimization function to integrate the similarity information of users and items under different semantic meta-paths, and a gradient descend solution is derived to optimize the objective function. Experiments with differ-This paper is an extension version of the PAKDD2016 Long Presentation paper "Dual Similarity Regularization for Recommendation" [40].

show abstract

Coupled Matrix Factorization Within Non-IID Context

Cited by 15 publications

References 17 publications

Improving stock market prediction via heterogeneous information fusion

Improving stock market prediction via heterogeneous information fusion

Context-Aware Recommendation Methods

Recommendation in heterogeneous information network via dual similarity regularization

Contact Info

Product

Resources

About