Evaluation of Adam, Nadam, RMSProp and SGD Optimization Algorithms on LSTM Model for JISDOR Exchange Rate Prediction
Keywords:
Jakarta Interbank Spot Dollar Rate (JISDOR), LSTM, Optimization Algorithm, Time SeriesAbstract
This research explores the application of four optimization algorithms—Adam, Nadam, RMSProp, and SGD—on a Long Short-Term Memory (LSTM) model to forecast the Jakarta Interbank Spot Dollar Rate (JISDOR). The volatile nature of exchange rate data, influenced by global and domestic economic dynamics, necessitates the use of models like LSTM that excel in capturing both short- and long-term dependencies. Performance was assessed using metrics such as Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). Among the optimizers, Nadam proved to be the most effective, achieving the lowest RMSE of 62.767 and a MAPE of 0.003, indicating its capability in managing complex fluctuations in the dataset. Despite Nadam's promising results, opportunities for improvement remain, including the inclusion of additional input variables, fine-tuning model parameters, and expanding the training dataset. This study underscores the critical role of selecting appropriate optimization algorithms for enhancing the accuracy of LSTM models in forecasting volatile financial time-series data, particularly for currency exchange rates.
References
Bekaert,, Geert , dan Robert Hodrick,. 2019. International Financial Management. Pearson Education. doi: http://dx.doi.org/10.1017/9781316282274.
Cai, Fang, Hyunsoo Joo, dan Zhiwei Zhang. 2020. “The impact of global economic events on currency exchange rates: Evidence from China.” Journal of International Economics. doi: http://dx.doi.org/10.2139/ssrn.1434412.
Chong , Eunsuk, Chulwoo Han, dan Franck. C Park. 2017. “Deep Learning Network for Stock Market Analysis and Prediction: Methodology, Data Representations and Case Studies.” Expert Systems with Applications 83: 187 - 205. doi: https://doi.org/10.1016/j.eswa.2017.04.030.
Dozat. T. 2016. “Dozat, T. (2016). Incorporating Nesterov momentum into Adam. ICLR Workshop.” Proceedings of the 4th International Conference on Learning Representations 11. doi: https://doi.org/10.4236/blr.2019.104046.
Greff, Klaus , Rupesh K Srivastava, Jan Koutnik, Bas R Steunebrink, dan Jurgen Schmidhuber. 2017. “LSTM: A Search Space Odyssey.” IEEE Transactions on Neural Networks and Learning Systems 28: 2222-2232. doi: https://doi.org/10.1109/TNNLS.2016.2582924.
Hochreiter, S.,, dan Schmidhuber, J. 1997. “Long short-term memory. Neural Computation.” 9: 1735–1780. doi:doi:10.1162/neco.1997.9.8.1735.
Hyndman, R. J , dan Athanasopoulos, G. 2018. Forecasting: principles and practice. OTexts.
Kingma, Diederik P, dan Jimmy Lei Ba. 2015. “Adam: A Method for Stochastic Optimization.” Published as a conference paper at the 3rd International Conference for Learning Representations. doi: https://doi.org/10.48550/arXiv.1412.6980.
Lecun, Y., Bottou, L., , Orr, G. B., dan Müller, K.-R. 2012. Efficient backprop. In Neural Networks: Tricks of the Trade. Springer.
Makridakis, S, S.C Wheelwright, dan V.E McGee. 1999. Metode Aplikasi Peramalan. Jakarta: Erlangga.
Reddi, S. J, Kale, S, dan Kumar, S. . . 2018. “On the convergence of Adam and beyond.” International Conference on Learning Representations (ICLR). doi: https://doi.org/10.48550/arXiv.1904.09237.
S. Ruder. 2016. An overview of gradient descent optimization. https://arxiv.org/abs/1609.047477.
Sule, A, dan Ozturk, H. . 2022. “The impact of global financial crises on exchange rate volatility.” Journal of Financial Economics, 35.
Sule, A., , dan Ozturk, H. 2022. “The impact of global financial crises on exchange rate volatility. Journal of Financial Economics.” Journal Of Financial Economics 102-112. doi: http://dx.doi.org/10.35527/kfedoi.2015.14.4.004.
Zahra, Hasna Haifa, Siti Saadah, dan Rita Rismala. 2021. “The Foreign Exchange Rate Prediction Using Long Short Term Memory: A Case Study in Covid-19 Pandemic.” International Journal on Information and Communication Technology 6: 94-105. doi: http://dx.doi.org/10.21108/IJOICT.2020.62.538.
