Service data prediction method and device, equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a service data prediction method and device, equipment and a storage medium, which are used for improving the prediction accuracy of service data. The service data prediction method comprises the steps of performing data cleaning and dimension value division on service order data and vehicle sales data crawled bya web crawler to obtain new vehicle data and old vehicle data; screening and combining dimension values in the new vehicle data and the old vehicle data to obtain a prediction dimension; predicting the service data of the new vehicle data and the old vehicle data in a preset time period through a preset prediction model, prediction dimensions and a preset prediction index to obtain new vehicle prediction data and initial old vehicle prediction data corresponding to each dimension; and performing merging processing on the new vehicle prediction data and the initial old vehicle prediction datacorresponding to each dimension to obtain service prediction data. In addition, the invention also relates to a blockchain technology, and new vehicle data and old vehicle data can be stored in the blockchain.

Description

technical field [0001] The invention relates to the field of intelligent decision-making of artificial intelligence, in particular to a business data prediction method, device, equipment and storage medium. Background technique [0002] With the rapid increase of business volume, for the prospect of the scale and development trend of the business volume, it is necessary to make statistical predictions on various data of the business volume, for example: forecasting of business data. The current forecasting method of business data generally adopts the integrated moving average autoregressive model (autoregressive integrated moving average model, ARIMA), and predicts business data at a preset time according to the time series forecasting algorithm in the ARIMA model and historical business data. Obtain forecast business data. [0003] However, the forecasting method of the above-mentioned business data is to directly fuse the historical business data of different business sce...

AI Technical Summary

Problems solved by technology

[0003] However, the forecasting method of the above-mentioned business data is to directly fuse the historical business data of different business scenarios together for forecasting, and the historical business data of different business scenarios will have different prediction rules, such as: the premium charging standard for new cars and old cars Inconsistency, with the special nature of their respective business scenarios, resulting in a low degree of fit between the business data prediction model and the business scenario, and a high deviation rate of the predicted business data, resulting in low accuracy of business data prediction

Images