Multivariable logistics freight volume prediction method based on LSTM network

Abstract

The invention discloses a multivariable logistics freight volume prediction method based on an LSTM network, which is used for solving the technical problem of low prediction precision in time seriesdata prediction in the prior art. The method comprises the following steps of: screening logistics freight volume influence factors and preprocessing influence factor data; converting a time series data set supervised learning mode; normalizing the time series data variables of the supervised learning format; dividing a data training set and a test set; setting parameters of an LSTM prediction model and carrying out forward training on the model; and performing back propagation of the model and back normalization of a logistics freight volume prediction value. According to the method, the long-term memorability of the LSTM network for the flow data is fully utilized, the relation between variables can be effectively explored through supervised learning, and the logistics freight volume prediction precision is improved.

Description

technical field [0001] The invention belongs to the technical field of machine learning and data prediction, and in particular relates to a multivariable logistics cargo volume prediction method based on an LSTM network. Background technique [0002] The forecast of logistics freight volume is one of the important basis for determining the development scale and logistics capacity level of logistics facilities in the region, planning the overall layout of logistics development in the region, and dividing the functions of logistics centers in the region. It is the primary preliminary work for regional logistics planning and decision-making. [0003] The forecast of logistics freight volume is to collect the historical demand data of logistics in the region, analyze the relationship between the change of logistics freight volume and various influencing factors, and use the influencing factors that can fully reflect the change trend of logistics freight volume to predict it. The...

AI Technical Summary

Problems solved by technology

Traditional artificial neural network methods often need to extract artificial feature parameters, which requires strong domain knowledge and experience, and shallow machine learning has limited ability to represent complex functions in the case of limited samples. The ability to transform is subject to certain restrictions, and the traditional shallow artificial neural network still has problems such as slow convergence speed and easy to fall into local optimal solution.

In addition, due to the weak nonlinear approximation ability of general regression models and artificial neural networks, it is difficult to adapt to multivariate time series forecasting problems

Images