Authors: Research Scholar Govind Kumar Verma, Associate Professor Dr. Richa Pareek
Abstract: Gold price forecasting plays a crucial role in financial investment planning, portfolio diversification and risk management because of the volatile nature of global financial markets. Accurate prediction is challenging because gold prices are influenced by multiple economic, financial, geopolitical and market-related factors. This study proposes a multi-factor machine learning framework for gold price forecasting and investment decision support, integrating machine learning, deep learning, financial analytics, sentiment analysis and optimisation techniques. The framework uses macroeconomic indicators, market volatility, inflation rates, exchange rates, commodity prices and financial news sentiment to improve forecasting accuracy and support strategic investment decisions. Fourteen studies published between 2020 and 2026 are reviewed and organised into three themes covering machine learning and deep learning techniques, multi-factor analytics and financial indicator integration, and intelligent investment decision support. The reviewed evidence is consolidated into comparative tables that map each study to its data context, method, principal finding and contribution to the proposed design, and seven research gaps are identified and mapped to corresponding research directions. The framework is specified through five factor blocks and six predictive components including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), CNN-LSTM, Support Vector Regression, Random Forest Regression and optimisation-based neural networks, together with a decision-support layer covering portfolio optimisation, risk assessment and adaptive forecasting. The findings indicate that multi-factor machine learning frameworks can enhance forecasting reliability, reduce prediction uncertainty and improve investment strategy optimisation in dynamic financial markets.
