An Extension of Laor Weight Initialization for Deep Time-Series Forecasting: Evidence from Thai Equity Risk Prediction

Katsamapol Petchpol () and Laor Boongasame
Additional contact information
Katsamapol Petchpol: Department of Computer Science, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand
Laor Boongasame: Department of Mathematics, Faculty of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok 10520, Thailand

Forecasting, 2025, vol. 7, issue 3, 1-27

Abstract: This study presents a gradient-informed proxy initialization framework designed to improve training efficiency and predictive performance in deep learning models for time-series forecasting. The method extends the Laor Initialization approach by introducing backward gradient norm clustering as a selection criterion for input-layer weights, evaluated through a lightweight, architecture-agnostic proxy model. Only the numerical input layer adopts the selected initialization, while internal components retain standard schemes such as Xavier, Kaiming, or Orthogonal, maintaining compatibility and reducing overhead. The framework is evaluated on a real-world financial forecasting task: identifying high-risk equities from the Thai Market Surveillance Measure List, a domain characterized by label imbalance, non-stationarity, and limited data volume. Experiments across five architectures, including Transformer, ConvTran, and MMAGRU-FCN, show that the proposed strategy improves convergence speed and classification accuracy, particularly in deeper and hybrid models. Results in recurrent-based models are competitive but less pronounced. These findings support the method’s practical utility and generalizability for forecasting tasks under real-world constraints.

Keywords: deep learning; financial risk prediction; time-series forecasting; Thai stock market; weight initialization (search for similar items in EconPapers)
JEL-codes: A1 B4 C0 C1 C2 C3 C4 C5 C8 M0 Q2 Q3 Q4 (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2571-9394/7/3/47/pdf (application/pdf)
https://www.mdpi.com/2571-9394/7/3/47/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jforec:v:7:y:2025:i:3:p:47-:d:1740771

Access Statistics for this article

Forecasting is currently edited by Ms. Joss Chen

More articles in Forecasting from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().