Proceedings of the 2023 1st International Conference on Advanced Informatics and Intelligent Information Systems (ICAI3S 2023)

<Previous Article In Volume
Next Article In Volume>

Enhancing Exchange Rate Forecasting: Leveraging Adaptive Moment Estimation in Deep Long Short Term Memory Models Against Foreign Currencies

Authors
Sugeng D. Cahyono1, Oliver S. Simanjuntak1, *, Heru C. Rustamaji1
1Department of Informatics, Faculty of Industrial Engineering, UPN Veteran Yogyakarta, Sleman, Yogyakarta, 55281, Indonesia
*Corresponding author. Email: oliver.simanjuntak@upnyk.ac.id
Corresponding Author
Oliver S. Simanjuntak
Available Online 2 February 2024.
DOI
10.2991/978-94-6463-366-5_22How to use a DOI?
Keywords
LSTM; forecasting; time series
Abstract

This study focuses on constructing a forecasting model for the Indonesian Rupiah exchange rate against the USD and JPY using DLSTM-ADAM. Exchange rate data from October 2014 to October 2022, sourced from the API website https://ofx.com, is utilized. The preprocessing stages involved normalization and feature sliding window applications. Subsequently, various hyperparameter combinations were employed to train and test the LSTM model. The outcomes emphasize the significance of adding hidden layers to the LSTM model, substantially reducing the RMSE and MAPE values, and enhancing the model’s overall performance. Furthermore, the study reveals that the Adam optimizer surpasses SGD regarding training performance. Specifically, for forecasting the IDR/USD exchange rate, the stacked layers and Adam optimizer yielded a remarkable 6,217% reduction in MAPE. Similarly, for the JPY/IDR exchange rate prediction, the MAPE reduction reaches 6,811%. These findings underscore the potential of this architecture for implementing effective time-series data-forecasting models.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2023 1st International Conference on Advanced Informatics and Intelligent Information Systems (ICAI3S 2023)
Series
Advances in Intelligent Systems Research
Publication Date
2 February 2024
ISBN
10.2991/978-94-6463-366-5_22
ISSN
1951-6851
DOI
10.2991/978-94-6463-366-5_22How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Sugeng D. Cahyono
AU  - Oliver S. Simanjuntak
AU  - Heru C. Rustamaji
PY  - 2024
DA  - 2024/02/02
TI  - Enhancing Exchange Rate Forecasting: Leveraging Adaptive Moment Estimation in Deep Long Short Term Memory Models Against Foreign Currencies
BT  - Proceedings of the 2023 1st International Conference on Advanced Informatics and Intelligent Information Systems (ICAI3S 2023)
PB  - Atlantis Press
SP  - 235
EP  - 247
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-366-5_22
DO  - 10.2991/978-94-6463-366-5_22
ID  - Cahyono2024
ER  -