Migration-crossover optimized graph-enhanced dual-level contextual fuzzy clustering for predicting oil and gold prices

The nation’s economy and the global environment are both greatly impacted by the price of crude oil. The strength of a nation’s economy is also reflected in the price of gold, which has an effect on the economy. Therefore, the most important and challenging issue is predicting non-linear oil and gold prices. Making wise financial decisions requires accurate oil and gold price forecasting. Conventional approaches are constrained in their ability to reflect these intricacies and interconnections in such dynamic and non-linear financial data. This paper presents a novel Graph Enhanced Dual-Level Contextual Fuzzy Clustering method optimized using the Migration-Crossover Algorithm (GDLFC-MCA) for predicting oil and gold prices. To identify intricate patterns and dependencies in market data, the proposed method combines sophisticated graph-based clustering techniques with dual-level contextual attention. The Migration-Crossover Algorithm (MCA) adjusts model parameters for the best results. In terms of accuracy, computational efficiency, and error reduction, experimental results on two benchmark datasets, the Brent crude oil dataset and the gold price dataset, show that GDLFC-MCA performs noticeably better than current approaches, attaining the best accuracy among them. The actual approach presented in this paper provides an accurate and highly efficient utilization of real-time prediction of the financial data, including oil and gold prices, with enhanced accuracy and reduced computational errors.