TY - GEN
T1 - Application of Voformer-EC Clustering Algorithm to Stock Multivariate Time Series Data
AU - Xin, Ning
AU - Khatoon, Shaheen
AU - Hasan, Md Maruf
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Clustering stocks based on similar increasing and decreasing trends pose a challenging problem in stock forecasting. Despite the extensive research on stock forecasting, striking a balance between effective clustering and computational speed remains an ongoing challenge. Traditional multivariate time series clustering methods are difficult to guarantee high speed with high accuracy. This study introduces the Voformer-EC model as a novel approach to address this issue, enhancing the analysis of multivariate time series data related to stocks. The Voformer-EC model incorporates time features and volatility, leveraging the Voformer neural network to extract time-related features and perform clustering. To evaluate its effectiveness, we applied the model to Nifty 50 Index data recorded every 60 minutes from February 2nd to February 28th, 2015, and compared it with a traditional approach. The results demonstrate a significant improvement in clustering accuracy using the Voformer-EC model. Building on these promising outcomes, future research aims to explore the application of the Voformer-EC model to temperature and precipitation data for identifying drought-prone areas. This implementation will enable targeted risk mitigation strategies to be employed effectively, advancing precision in addressing climate-related challenges.
AB - Clustering stocks based on similar increasing and decreasing trends pose a challenging problem in stock forecasting. Despite the extensive research on stock forecasting, striking a balance between effective clustering and computational speed remains an ongoing challenge. Traditional multivariate time series clustering methods are difficult to guarantee high speed with high accuracy. This study introduces the Voformer-EC model as a novel approach to address this issue, enhancing the analysis of multivariate time series data related to stocks. The Voformer-EC model incorporates time features and volatility, leveraging the Voformer neural network to extract time-related features and perform clustering. To evaluate its effectiveness, we applied the model to Nifty 50 Index data recorded every 60 minutes from February 2nd to February 28th, 2015, and compared it with a traditional approach. The results demonstrate a significant improvement in clustering accuracy using the Voformer-EC model. Building on these promising outcomes, future research aims to explore the application of the Voformer-EC model to temperature and precipitation data for identifying drought-prone areas. This implementation will enable targeted risk mitigation strategies to be employed effectively, advancing precision in addressing climate-related challenges.
KW - Multivariate Time Series Clustering
KW - Voformer-EC Neural Network
KW - Volatility Activation Function
UR - http://www.scopus.com/inward/record.url?scp=85186760765&partnerID=8YFLogxK
U2 - 10.1109/CyberC58899.2023.00027
DO - 10.1109/CyberC58899.2023.00027
M3 - Conference Proceeding
AN - SCOPUS:85186760765
T3 - Proceedings - 2023 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2023
SP - 100
EP - 107
BT - English
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2023
Y2 - 2 November 2023 through 4 November 2023
ER -