Data prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a data prediction method and device, electronic equipment and a storage medium. The method comprises the steps: for any optional model in a target scene, acquiring evaluation samples of the target scene, a true value corresponding to each evaluation sample and an estimated value of the model for each evaluation sample, wherein the target scene comprises an expectation maximization scene for target parameters; sorting the evaluation samples according to a first sorting mode taking the estimated value of each evaluation sample as a reference, and obtaining a first evaluation parameter of the model according to a difference value of real values corresponding to any two adjacent evaluation samples after the sorting; determining a target model matched with the target scene according to the first evaluation parameter and the second evaluation parameter of each model; and obtaining prediction data of the target parameter of any object in the target scene through the target model. Therefore, a more reasonable and accurate evaluation mode is provided to adapt to models in different scenes, and the accuracy of a data prediction result is further improved.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular to a data prediction method, device, electronic equipment and storage medium. Background technique [0002] In machine learning, we need an offline evaluation method for the trained model, so that we can compare the quality of the model before going online. Especially in application scenarios where revenue maximization, click-through rate maximization, etc. are expected to be maximized, the performance of the selected model is very important. [0003] Take advertising GMV (Gross MerchandiseVolume, website transaction amount) estimation as an example. In order to increase the website transaction amount, you can recommend products with larger amounts to users. The model here estimates the price of commodities on the website. Currently, RMSE (RootMean Squard) is generally used. Error, square root error) is used as a measure of the model to evaluate whether the v...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a data prediction method, device, electronic equipment and storage medium to solve the problem of low accuracy of model prediction results in related technologies

Images