Category inventory prediction method and prediction device

Abstract

The invention provides a category inventory prediction method and a prediction device. On one hand, the existing prediction technology gets rid of the dependence on a condition of stable inventory sequence, and on the other hand, limitation of data size scale insufficiency on learning algorithm can also be avoided, so that an unstable category inventory sequence can be greatly predicted. According to a technical scheme provided by the invention, not only can the operation capability of E-business enterprises be improved, but also reasonable and optimal distribution of a social resource is importantly influenced. The category inventory prediction method comprises: obtaining the category inventory sequence from a data platform, and performing standard processing on the sequence; decomposing the standard sequence into a plurality of intrinsic mode functions; predicting each intrinsic mode function to obtain multiple prediction results; collecting multiple prediction results, thereby obtaining a prediction result of the category inventory.

Description

technical field [0001] The invention relates to the technical field of computers and software thereof, in particular to a method and device for predicting category inventory. Background technique [0002] In recent years, with the rapid development of modern information technology represented by the Internet, especially mobile payment, social network, search engine and cloud computing, the Internet has gradually attracted the attention of the whole society. Each e-commerce platform has also ushered in its best development opportunities. As a highly systematic activity, inventory management is closely related to and inseparable from the capital flow, information flow, and logistics of e-commerce companies. It determines the resource allocation capabilities of e-commerce companies and is related to the lifeline of e-commerce companies. An efficient inventory management system can not only improve the operational capabilities of e-commerce companies, but also play an important...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, the basic condition for the ARIMA model to be applied to category inventory forecasting is to require the category inventory sequence to satisfy the condition of stationarity, that is, the individual value should fluctuate around the mean value of the sequence, and there should be no obvious upward or downward trend

For the category inventory sequence showing an upward or downward trend, although the ARIMA model has a differential smoothing preprocessing mechanism for the original sequence, this lack of adaptive processing method cannot guarantee the sequence stability, so the predicted results are in Accuracy is still lacking

On the other hand, although the learning algorithm has received a lot of attention in recent years, it has relatively high requirements for the size of the training samples. Only when the size of the training samples is large enough, the prediction results will be more accurate; for problems with relatively small sequence sizes, This type of algorithm still cannot overcome the difficulty of non-stationary sequence

[0005] To sum up, on the one hand, the existing technology cannot get rid of the dependence on the condition that the inventory sequence is stable, and on the other hand, it has relatively high requirements on the size of the training samples

Therefore, the accuracy of the prediction results for non-stationary sequences or sequences whose sequence size does not meet the requirements cannot be guaranteed.

This not only fails to improve the operational capabilities of e-commerce companies, but also has a certain impact on the rational and optimal allocation of social resources.

Images