Constructing a multilayer network for stock market

Chen, Wei; Jiang, Manrui; Jiang, Cheng

doi:10.1007/s00500-019-04026-y

Cited by 15 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The edges were considered to be formed if 𝜌 ≥ 0.7, which is taken in the adjacency matrix (A xy ) as 1 and 0 if 𝜌 > 0.7. [27,33] The graph was constructed using the "igraph" package in the RStudio software and visualised using Gephi 0.9.2. The features of the graph, [29] such as the number of edges (E), network diameter (D), average path length (L), graph density (G), degree centrality (DC), and closeness centrality (CC) were also computed using the RStudio software.…”

Section: Methodsmentioning

confidence: 99%

How the Complex Network of Specklegram Deciphers Intra‐Film Thermal Induced Dynamics?

Sankararaman

2021

Annalen der Physik

View full text Add to dashboard Cite

The present work deciphers the potential of the graph and its features in the speckle-based nondestructive evaluation of intra film thermal-induced dynamics. The molybdenum oxide film, prepared by sputtering technique, containing nanorods is subjected to thermal stress from 30-50 °C and the specklegrams are recorded. The co-occurrence matrix (CM) and heat map analyses of the specklegrams by dividing the temperature range into four intervals of 5 °C each reveal that the thermal stress drives the film from a less stable to a more stable state from the third to the fourth temperature interval. The CM analysis indicates the thermal-induced rearrangements among the nanorods of the film. By extracting frames from the videograph of the speckle pattern during temperature variation, a complex network is constructed, taking the middle column of each frame as a node. The graph features also become minimum in the third interval and increase in the fourth interval revealing that the film moves to a more ordered state under thermal stress. The analysis of the specklegram by CM, heat map, and graph suggests that graph features present a high sensitivity compared to the other methods.

show abstract

Section: Methodsmentioning

confidence: 99%

How the Complex Network of Specklegram Deciphers Intra‐Film Thermal Induced Dynamics?

Sankararaman

2021

Annalen der Physik

View full text Add to dashboard Cite

show abstract

“…Chen et al 12,13 developed a multilayer network by combining the GC, PC, and conditional probability-based non-linear relation network to describe the linear and non-linear relationship among stock markets. Zhong et al 28 modeled the stock markets relationship by using a dynamic financial network constructed by Spearman's correlation and demonstrate that the dynamic model not only shows the structural explanation of the economic market but is also used to predict it.…”

Section: Literature Surveymentioning

confidence: 99%

“…In recent studies, 9–11 deep learning models have been extensively utilized for stock price time series forecasting using historical stock prices. There are primary three paradigms of deep learning: convolution neural network (CNN), 12,13 recurrent neural network (RNN), 14 and deep belief network 15 widely used for stock price forecasting. Deep learning approaches can help identify patterns in historical data and make predictions based on those patterns.…”

Section: Introductionmentioning

confidence: 99%

Stock price forecasting based on the relationship among Asian stock markets using deep learning

Kumar

Singh

Jain³

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe stock price fluctuation of one country can be influenced by the movement of the stock price of other countries implying that there exists some relationship among various stock markets. This study examines the interrelationship among Asian stock markets and forecasts the stock market on the basis of the relationship that exists among Asian stock markets. The interrelationship is tested by using the Granger causality (GC) test and Pearson's correlation (PC) matrix. Further, a deep learning model namely a long short term memory (LSTM) neural network is utilized to forecast the stock price of one country by using the price of other countries that have a correlation and causal relationship with the target stock market. PC matrix shows that there exists a strong correlation among Asian stock markets. Results from the GC show that there exists a unidirectional relationship between Sensex and NIKKEI 225 to SSE composite index, Sensex to NIKKEI 225, and Sensex and TSEC weighted index to KOSPI composite index and a bi‐directional relationship among Sensex, TSEC weighted index and Hang Seng index. Experimental results show that GC and LSTM‐based model namely GC‐LSTM shows better forecasting performance in comparison to PC and LSTM‐based model termed as PC‐LSTM.

show abstract

“…The first stage of our approach is to identify vertex clusters on the network. Various studies have shown that clusters are stronger in financial threshold networks [1,6,12,35]. The presented novel threshold method works with very low computational complexity depending on the spectrum of the network's Laplacian matrix.…”

Section: Introductionmentioning

confidence: 99%

Hierarchies in communities of UK stock market from the perspective of Brexit

Balcı

Akgüller

Güzel

2020

Journal of Applied Statistics

View full text Add to dashboard Cite

Nowadays, increase of analyzing stock markets as complex systems lead graph theory to play a key role. For instance, detecting graph communities is an important task in the analysis of stocks, and as planar maximally filtered graphs let us to get important information for the topology of the market. In this study, we first obtain correlation network representation of UK's leading stock market network by using a novel threshold method. Then, we determine vertex clusters by using modularity and analyze clusters in planar maximally filtered graph substructures. Our analyze include a new measure called weighted Gini index for measuring the sparsity. The main goal of this paper is to study the hierarchical evolution of the market communities throughout the Brexit referendum, which is known as the stress period for the stock market. Hence, the overall sample is divided into two sub-periods of pre-referendum, and post-referendum to obtain communities and hierarchical structures. Our results indicate that financial companies are leading elements of the clusters. Moreover, the significant changes within the network topologies are observed for insurance, consumer goods, consumer services, mining, and technology sectors whereas oil and gas and health care sectors have not been affected by Brexit stress.

show abstract

Constructing a multilayer network for stock market

Cited by 15 publications

References 42 publications

How the Complex Network of Specklegram Deciphers Intra‐Film Thermal Induced Dynamics?

How the Complex Network of Specklegram Deciphers Intra‐Film Thermal Induced Dynamics?

Stock price forecasting based on the relationship among Asian stock markets using deep learning

Hierarchies in communities of UK stock market from the perspective of Brexit

Contact Info

Product

Resources

About