Claim Missing Document
Check
Articles

Found 1 Documents
Search

Performance Comparison of Long Short-Term Memory and Convolutional Neural Network for Prediction of Exchange Rate of Indian Rupee against US Dollar Rai, Kovat; Vijayan, Amit
International Journal Artificial Intelligent and Informatics Vol 3, No 1 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (438.98 KB) | DOI: 10.33292/ijarlit.v3i1.41

Abstract

This study compares the effectiveness of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) models in predicting the exchange rate of the Indian Rupee (INR) against the United States Dollar (USD). Using historical data from 2017 to 2023 obtained from Yahoo Finance, both models were trained and evaluated based on several performance metrics including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), coefficient of determination (R²), and accuracy. The results showed that the hybrid LSTM model consistently outperformed the CNN model on all evaluation metrics, with a Test RMSE value of 0.38 compared to 1.32 for CNN. The LSTM model also showed better stability between training and testing performance, indicating better generalization ability and lower risk of overfitting. These findings confirm the superiority of the LSTM architecture in capturing the complex temporal patterns inherent in financial time series data, making it a more reliable option for currency exchange rate prediction.