Modeling dynamic elasticity on intraday volatility and volume by finding PDEs using machine learning
Document Type
Conference Proceeding
Publication Date
1-1-2024
Abstract
The study proposes a methodology to identify a PDE describing the relationship between trading volume and volatility in securities, focusing on the SPDR S& P 500 ETF (SPY) as a case study. By integrating ML exploration with domain expertise, the study uncovers a simple and interpretable PDE, providing insights into market behavior and enhancing market monitoring capabilities for traders and investors. The approach emphasizes the importance of combining ML methods with domain knowledge to derive meaningful insights and practical applications in financial markets.
Identifier
85198838794 (Scopus)
ISBN
[9798350387803]
Publication Title
2024 IEEE 5th World AI IoT Congress, AIIoT 2024
External Full Text Location
https://doi.org/10.1109/AIIoT61789.2024.10578976
First Page
444
Last Page
450
Recommended Citation
Li, David D.; Li, Angela; Mensing, Rodger; and Li, Zy, "Modeling dynamic elasticity on intraday volatility and volume by finding PDEs using machine learning" (2024). Faculty Publications. 952.
https://digitalcommons.njit.edu/fac_pubs/952