Gold price prediction using transformers

• المؤلف الرئيسي: Wong, Stanley Qi Ren
• مؤلفون آخرون: Wang Lipo
• التنسيق: Final Year Project
• اللغة: English
• منشور في: Nanyang Technological University 2023
• الموضوعات: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/172705
• المؤسسة: Nanyang Technological University

Gold is a cornerstone asset of human history, and its price can fluctuate depending on various circumstances, therefore, being able to predict the price of gold is an essential task in financial forecasting, as it impacts economic strategies and investment decisions. Previously, classical methods like ARIMA and GARCH were used to predict prices. With the rise of neural networks, ML and AI methods like LSTM show better performances compared to classical methods. Transformers have asserted their dominance in the field on NLP when compared to LSTM, this investigation is to determine whether they can perform better than other methods and how can it be optimized for forecasting the price of gold.