Logistics demand prediction using fuzzy support vector regression machine based on Adam optimization

As the digital economy experiences swift advancements, demand prediction in logistics holds a crucial significance for firms operating in the logistics sector. The primary aim of this research paper is to ascertain the optimal method for forecasting logistics demand based on the logistics demand data from the Chengdu-Chongqing Dual-City Economic Circle (CC-DEC). The importance and widespread application of machine learning technologies in intelligent forecasting are undeniable. Specifically in Logistics Demand Prediction, Support Vector Regression plays a pivotal role in enhancing accuracy. Precise prediction of logistics demand is essential for optimizing resource allocation efficiency, which is the core focus of this research endeavor. In this study, we conduct the Fuzzy Support Vector Regression Machine approach based on Adam optimization (FSVR-AD). Then we have developed a comprehensive Logistics Demand Prediction index system tailored for the CC-DEC in China, particularly focusing on the dimensions of carbon neutrality and carbon peaking. Three distinct forecasting models are constructed on historical data spanning from 2005 to 2021, aiming to accurately predict the logistics demand within the economic circle. Our analysis reveals that all three models exhibit high predictive accuracy. However, the FSVR-AD demonstrates superior performance, as its predictions align more closely with actual values, resulting in reduced error margins. Given its accuracy and precision, the FSVR-AD is an ideal choice for constructing logistic demand forecasts. Its predictions offer a reliable reference for strategic planning in logistics management, enabling companies to optimize automation and innovate supply chain processes to align with evolving trends.