About this document

Spatio-Temporal Model For Limit Order Books in The Stock Exchange of Thailand by Keing Ruekpisut is a document available to read on EtoBox.

This document presents a spatio-temporal model utilizing deep neural networks to predict anomaly price movements in the Stock Exchange of Thailand using limit order books. The study compares the performance of convolutional neural networks, Long short-term memory models, and their combination, finding the latter to achieve the highest accuracy of 74.55% in classifying price movements. The model aims to enhance the detection of abnormal trading behaviors that can manipulate stock prices.

Author

Keing Ruekpisut

Language

EN