Global currency monitoring system

• Main Author: Satish, Prabhagar @ Nagaiah
• Format: Final Year Project / Dissertation / Thesis
• Published: 2023
• Subjects: HG Finance; T Technology (General)
• Online Access: http://eprints.utar.edu.my/5999/1/fyp_IA_2023_SP.pdf; http://eprints.utar.edu.my/5999/

In recent years, there has been a growing popularity in currency trading within the foreign exchange (Forex) market. Traders consistently seek novel strategies to gain an edge in predicting market trends and executing profitable transactions. This research focuses on the construction of a machine learning model that use a combination of technical indicators and fundamental factors to predict Forex prices and RSI values. The model's training method incorporates a neural network, which leverages past data to acquire knowledge of the patterns and interconnections among different market elements. Metrics such as accuracy, precision, recall, and F1 score are commonly employed in the evaluation of the proposed model. However, there are other measures that play a significant part in model evaluation, such as Mean Absolute Error (MAE) and Mean Squared Error (MSE). The results suggest that the model exhibits a higher level of proficiency compared to traditional statistical models when it comes to predicting RSI values and changes in Forex prices. The proposed model is evaluated in comparison to the baseline model in terms of its accuracy, and the results demonstrate that the proposed model outperforms the baseline model in terms of accuracy. Furthermore, the F1 score of the proposed model is compared to that of the baseline model, revealing that the suggested model achieves a higher F1 score in comparison to the baseline model. Furthermore, the present study aims to examine the impact of various technological aspects on the performance of the model. The results indicate that specific indicators, such as the moving average, have a significant role in predicting the values of the relative strength index (RSI) and Forex prices. This study highlights the potential of machine learning in the financial industry, particularly in the prediction of market movements and its application in facilitating trading decisions. In general, the research underscores the potential of machine learning inside the financial sector. The proposed methodology exhibits promise in augmenting the precision of Forex price and RSI value forecasts, hence potentially resulting in more profitable trades for traders. The acronym RSI denotes the relative strength index. In order to enhance the precision of the model, future research endeavours may explore the potential inclusion of basic elements with intricate technical indicators.