Intelligent Decision Making for Commodities Price Prediction: Opportunities, Challenges and Future Avenues

The global economies depend heavily on commodity prices, which have an effect on businesses, investors, and consumers worldwide. It is important to be able to estimate commodity prices accurately because it facilitates risk management, distribution of resources, and intelligent decision-making. For the current status of research in this area, this study gives a systematic review of the available commodity price prediction models specifically for house prices in real estate. We determine and compare different commodity price prediction models and techniques used in academic and commercial settings. The paper is divided into three primary categories: house price prediction, stock price prediction, and natural gas price prediction. Within each category, various methodologies are utilized, including ensemble methods, neural networks, support vector machines, time series analysis, and regression analysis. This review offers a thorough analysis of both the strengths and limitations of current models, as well as the major variables affecting their performance. Additionally, potential challenges associated with models are discussed, and insights are provided for addressing different prediction issues. The review serves as an invaluable guide for researchers, practitioners, and policymakers seeking to gain deeper knowledge of the latest advancements in commodity price prediction. The findings indicate that machine learning holds significant potential for optimizing house price predictions.