An improved machine learning model Shapley value-based to forecast demand for aquatic product supply chain

Previous machine learning models usually faced the problem of poor performance, especially for aquatic product supply chains. In this study, we proposed a coupling model Shapely value-based to predict CCL demand products (CCLD-AP). We first select key impact indicators through gray correlation degree and finally determine indicator system. Secondly, prediction, principal component regression analysis BP neural network are constructed from perspective time series, linear nonlinear, combined with three single forecasts, forecasting is constructed, error all prediction results shows that more accurate. Finally, trend extrapolation method series independent variable influencing factor value CCLD-AP 2023 2027. Our study can provide reference progress in ports their hinterland cities.