ESROP – Time-Series Data Modelling and Analysis with a Focus on Pattern Analysis

The research addresses the fundamental trade-off in financial econometrics between computational efficiency and predictive accuracy under varying market conditions. While existing literature has established hybrid models with high predictive capabilities, these often incur high computational costs that may not be necessary during stable market regimes. Conversely, traditional regime-switching models like the MS-GARCH utilize a Markov switch to adjust parameters but often lack the predictive depth required for unstable periods.

This project aims to bridge the gap by developing a mechanism that implements Markov switches between GARCH and LSTM architectures based on the detected regime.

Faculty Supervisor:

Arthur Chan

Student:

Partner:

King Mongkut’s University of Technology Thonburi

Discipline:

Engineering

Sector:

Artificial Intelligence; Finance and Insurance

University:

University of Toronto

Program: