Counterfactual explanations for forex prediction using deep learning methods
Fund managers and traders in the Forex trading market have increasingly moved to electronification of their trade execution which provides an opportunity and incentive to perform time series forecasting. However, black-box models lack explainability in their decision-making, especially in the domain...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/175238 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-175238 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1752382024-04-26T15:42:01Z Counterfactual explanations for forex prediction using deep learning methods Vinod, Vinay Krishnaa Fan Xiuyi School of Computer Science and Engineering xyfan@ntu.edu.sg Computer and Information Science Counterfactual explanations Forex trading prediction Fund managers and traders in the Forex trading market have increasingly moved to electronification of their trade execution which provides an opportunity and incentive to perform time series forecasting. However, black-box models lack explainability in their decision-making, especially in the domain of the target audience. This study presents a Deep Learning (DL) approach to time series forecasting and thereafter applies a novel counterfactual explanation as an alternative approach to model explainability. Past research has shown the effectiveness of DL Models such as LSTM in performing time series forecasting in a financial context. This study aims to build on foundational DL models to generate ‘What-If’ alternative scenarios based on a desired outcome. The study optimizes different parts in the counterfactual generation process to the context of a Forex data stream. The research has conclusively achieved high accuracy in a three-day forecast of its generated counterfactual scenario with a validity score of 0.8201. This study and its areas of future work have the potential to create an invaluable impact on the workflows of stakeholders in the fund management and trading sectors, thereby making a breakthrough for explainable AI in the world of finance. Bachelor's degree 2024-04-23T00:50:27Z 2024-04-23T00:50:27Z 2024 Final Year Project (FYP) Vinod, V. K. (2024). Counterfactual explanations for forex prediction using deep learning methods. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175238 https://hdl.handle.net/10356/175238 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science Counterfactual explanations Forex trading prediction |
spellingShingle |
Computer and Information Science Counterfactual explanations Forex trading prediction Vinod, Vinay Krishnaa Counterfactual explanations for forex prediction using deep learning methods |
description |
Fund managers and traders in the Forex trading market have increasingly moved to electronification of their trade execution which provides an opportunity and incentive to perform time series forecasting. However, black-box models lack explainability in their decision-making, especially in the domain of the target audience. This study presents a Deep Learning (DL) approach to time series forecasting and thereafter applies a novel counterfactual explanation as an alternative approach to model explainability. Past research has shown the effectiveness of DL Models such as LSTM in performing time series forecasting in a financial context. This study aims to build on foundational DL models to generate ‘What-If’ alternative scenarios based on a desired outcome. The study optimizes different parts in the counterfactual generation process to the context of a Forex data stream. The research has conclusively achieved high accuracy in a three-day forecast of its generated counterfactual scenario with a validity score of 0.8201. This study and its areas of future work have the potential to create an invaluable impact on the workflows of stakeholders in the fund management and trading sectors, thereby making a breakthrough for explainable AI in the world of finance. |
author2 |
Fan Xiuyi |
author_facet |
Fan Xiuyi Vinod, Vinay Krishnaa |
format |
Final Year Project |
author |
Vinod, Vinay Krishnaa |
author_sort |
Vinod, Vinay Krishnaa |
title |
Counterfactual explanations for forex prediction using deep learning methods |
title_short |
Counterfactual explanations for forex prediction using deep learning methods |
title_full |
Counterfactual explanations for forex prediction using deep learning methods |
title_fullStr |
Counterfactual explanations for forex prediction using deep learning methods |
title_full_unstemmed |
Counterfactual explanations for forex prediction using deep learning methods |
title_sort |
counterfactual explanations for forex prediction using deep learning methods |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/175238 |
_version_ |
1806059763448938496 |