Prediction method and device of commodity price

Abstract

The present invention provides a commodity price prediction method and device, the method comprising: acquiring historical price information of commodities to be predicted corresponding to multiple first historical time points, historical weather index information corresponding to multiple second historical time points, and Forecast weather index information corresponding to multiple future time points; build a price prediction model based on historical price information and historical weather index information and train the price prediction model; treat the price of the forecast commodity based on the trained price prediction model and forecast weather index information Forecasting is performed to obtain forecasted commodity price values ​​corresponding to multiple future time points. In the embodiment of the present invention, by adding an anchor factor that can predict the trend in advance in the price prediction model, instead of relying on the explained variable itself to calculate the later prediction based on the previous prediction, the calculation error is reduced, thereby improving the price prediction model. Confidence in long-term forecasts.

Description

technical field [0001] The present invention relates to the technical field of data analysis, in particular to a commodity price prediction method and device. Background technique [0002] The forecast method of commodity price is the basis of market forecast analysis and commodity production and sales decision-making. It is an important issue in the field of market forecast and plays a key role in many problems such as commodity production and sales. The versatility and accuracy have a great influence. [0003] Traditional forecasting of commodity price trends is limited by the difficulty of obtaining explanatory variable data, so time series analysis is often used, and the lagged item of the explained variable is used as the explanatory variable in the model, that is, the explained variable is calculated based on the basic explanatory variable. After the variables are calculated, the calculated explained variables are used as new explanatory variables to calculate the sub...

AI Technical Summary

Problems solved by technology

[0004] But in fact, when the explained variables are calculated, certain errors will be introduced

Using the calculated explained variable as a new explanatory variable to calculate the subsequent explained variable will lead to the continuous accumulation and amplification of this error, which will eventually lead to an exponential decrease in the credibility of the medium and long-term forecast value.

Images