A Data Science-Based Forex Prediction System (EUR/USD) With Integrated Machine Learning and a Web Dashboard

The rapid development of information technology has driven significant transformations in various sectors, including the global financial sector. One of the most dynamic financial instruments is foreign exchange (forex), the trading of foreign currencies, which plays a crucial role in international economic activity. However, the high volatility and complexity of factors influencing exchange rates make predicting forex price movements a significant challenge. Conventional approaches such as fundamental and technical analysis are limited by their subjective nature and inability to recognize non-linear patterns in price data. This research aims to develop a data science-based forex prediction system with the integration of machine learning algorithms and an interactive web dashboard. The models used include Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), designed to analyze time series data and capture long-term patterns in the EUR/USD currency pair's price movements. The development process follows the CRISP-DM (Cross Industry Standard Process for Data Mining) stages, including data understanding, data preparation, modeling, evaluation, and system implementation. Thus, this research provides two main contributions: (1) academically, strengthening the application of Machine Learning methods in the field of digital finance based on Data Science, and (2) practically, producing a prototype of an interactive forex prediction system that can be used as a decision support system for traders and financial analysts.