Method for predicting material purchasing demand based on LSTM network

Abstract

The invention discloses a method for predicting a material purchasing demand based on an LSTM network. The method comprises the following steps: S1, carrying out data processing on pre-collected databy adopting a preset method; S2, comparing the original prediction model with the recurrent neural network model through a preset method; S3, constructing an LSTM model by adopting a preset method, and taking the processed data as the input of the LSTM model to obtain a predicted value. The invention has the beneficial effects that through the construction and training of the LSTM network-based material purchasing prediction model, the LSTM model can remember a long-term state under the action of three paths of input data, so the problem of long-distance dependence can be effectively solved; compared with a traditional original prediction model, the model effectively improves the prediction accuracy.

Description

technical field [0001] The present invention relates to the technical field of methods for forecasting demand for material procurement, in particular, to a method for forecasting demand for material procurement based on an LSTM network. Background technique [0002] At present, with the rapid development of my country's social economy, various functional departments, such as the electric power department, have higher and higher demand for materials, which promotes the prosperity of the power grid engineering market and poses greater challenges to related enterprises. Only by further optimizing enterprise management And all kinds of resource allocation, improve resource utilization and engineering design and development efficiency, in order to adapt to the new market situation and meet various challenges. [0003] Taking the power sector and enterprises as examples, how to accurately predict the material demand of substations and distribution network projects, improve the util...

AI Technical Summary

Problems solved by technology

[0005] However, the existing demand forecasting model for procurement materials has the following defects: 1. Data redundancy, discrete, large fluctuations in item purchases, no data cleaning for procurement data, ignoring the impact of outliers on forecasting; 2. Procurement There are too many factors affecting demand, and the ordinary linear regression model cannot fit the prediction function well; 3. The time series relationship between historical purchases is not considered, and the prediction accuracy is low

Images