Prediction model adjusting method and device

Abstract

The invention provides a prediction model adjusting method and device, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring transaction data of a transaction object in a preset time period, and preprocessing the transaction data to obtain transaction feature data; based on the transaction feature data and a market mobility prediction model, obtaining a mobility prediction value of the transaction object, wherein the mobility prediction value is equal to the sum of the products of the prediction results of the sub-models and the corresponding weights; obtaining an actual liquidity value of the transaction object based on the liquidity parameter corresponding to the transaction object in the preset time period; and adjusting the weight corresponding to each sub-model according to the actual mobility value of the transaction object and the prediction result of each sub-model. The device is used for executing the method. According to the prediction model adjusting method and device provided by the embodiment of the invention, the accuracy of model prediction is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method and device for adjusting a prediction model. Background technique [0002] At present, the traditional prediction model realizes the training of various machine learning models by dividing the sample set into training set and test set, and then applies the trained model to the actual production environment for prediction. [0003] In order to improve the accuracy of model prediction, an integrated model composed of multiple sub-models is used for prediction in practical applications. In the prior art, multiple sub-models are often specified at the beginning of the training of the machine learning model, and can be applied to the actual production environment after the training of multiple models is completed. Due to changes in the actual production environment data, after a period of use, the prediction accuracy of the integrated model will decrease. Usu...

AI Technical Summary

Problems solved by technology

Due to changes in the actual production environment data, after a period of use, the prediction accuracy of the integrated model will decrease. Usually, the training data will be updated to retrain each sub-model, which will consume a lot of time and cost.

Images