Advancing Exchange Rate Forecasting: Leveraging Machine Learning and AI for Enhanced Accuracy in Global Financial Markets

2025-06-11

AI Summary

To address the low predictive accuracy of USD/BDT exchange rate forecasting, this paper proposes an LSTM-GBC hybrid framework: LSTM captures temporal dynamics for high-precision numerical prediction, while Gradient Boosting Classifier (GBC) leverages volatility features—particularly normalized daily returns—to classify directional movement. This work represents the first application of LSTM jointly with a gradient boosting classifier for BDT exchange rate prediction and introduces normalized daily returns as a novel short-term volatility indicator. Evaluated on 2018–2023 data, the LSTM achieves 99.449% numerical prediction accuracy (RMSE = 0.9858), and GBC-guided simulated trading yields a 40.82% return—substantially outperforming ARIMA and other benchmarks. The framework balances predictive accuracy, directional robustness, and interpretability, offering a reliable decision-support tool for cross-border trade operations and macroprudential risk management in Bangladesh.

Technology Category

• Machine Learning: Bayesian Learning
• Natural Language Processing: Learning & Optimization for NLP
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The prediction of foreign exchange rates, such as the US Dollar (USD) to Bangladeshi Taka (BDT), plays a pivotal role in global financial markets, influencing trade, investments, and economic stability. This study leverages historical USD/BDT exchange rate data from 2018 to 2023, sourced from Yahoo Finance, to develop advanced machine learning models for accurate forecasting. A Long Short-Term Memory (LSTM) neural network is employed, achieving an exceptional accuracy of 99.449%, a Root Mean Square Error (RMSE) of 0.9858, and a test loss of 0.8523, significantly outperforming traditional methods like ARIMA (RMSE 1.342). Additionally, a Gradient Boosting Classifier (GBC) is applied for directional prediction, with backtesting on a $10,000 initial capital revealing a 40.82% profitable trade rate, though resulting in a net loss of $20,653.25 over 49 trades. The study analyzes historical trends, showing a decline in BDT/USD rates from 0.012 to 0.009, and incorporates normalized daily returns to capture volatility. These findings highlight the potential of deep learning in forex forecasting, offering traders and policymakers robust tools to mitigate risks. Future work could integrate sentiment analysis and real-time economic indicators to further enhance model adaptability in volatile markets.

Problem

• Improving USD/BDT exchange rate forecasting accuracy using machine learning.
• Comparing LSTM and GBC models against traditional methods like ARIMA.
• Enhancing forex risk management tools for traders and policymakers.

Innovation

• LSTM neural network for high accuracy forex prediction
• Gradient Boosting Classifier for directional trade analysis
• Normalized daily returns to capture market volatility