Foreign Exchange Rate Prediction Using Long-Short Term Memory:
A Case Study in COVID-19 Pandemic

HASNA HAIFA ZAHRAH

Informasi Umum

Kode

21.04.1331

Klasifikasi

006.31 - Machine Learning

Jenis

Karya Ilmiah - Skripsi (S1) - Reference

Subjek

Machine - Learning

Dilihat

271 kali

Informasi Lainnya

Abstraksi

The foreign exchange market is a global financial market that is influenced by economic, political, and psychological factors that are interconnected in complex ways. This complexity makes the foreign exchange market a difficult time-series prediction. At the end of 2019, the world was faced with the COVID-19 pandemic that has not only affected public health but also the foreign exchange market, which makes the trading behaviour affected. Long Short-Term Memory network (LSTM) is a type of recurrent neural network (RNN) that can solve long-term dependencies and is suitable to be a financial time-series model. This study implemented the LSTM model to predict the foreign exchange rate at a timeframe of 1 hour and daily in 2020 to get the best hyperparameter based on the RMSE evaluation results. Furthermore, with the hyperparameters obtained, the prediction result of 2020 was then compared with the 2018 and 2019 prediction results. The results showed that the best hyperparameters in the daily timeframe were found to be 2 hidden layers and 10 neurons with a dropout layer. Meanwhile, the best hyperparameters in 1-hour timeframe were found to be 1 hidden layer and 5 neurons without a dropout layer. The best RMSE result was obtained in 1-hour timeframe and when 2020’s RMSE result was compared to 2018’s and 2019’s RMSE result, the prediction of 2019 gave the best RMSE result. The COVID-19 pandemic has quite an impact on the model's performance when compared to 2018 and 2019. However, the LSTM model still able to give good results in the 2020 prediction, proven by the RMSE result which is 0,135×10^(-2).