A method and system for optimizing a predictive model for a DSP platform

Abstract

The present application relates to the technical field of data processing, and particularly relates to a method and system for optimizing a prediction model for a DSP platform. The method comprises: creating an experiment directory; based on a data synchronization protocol, pulling sample data from a preset pre-stored data directory or a remote database to the experiment directory; preprocessing a target file under the experiment directory to obtain preprocessed data; based on a preset rule for unifying an input format, standardizing, then based on a result of standardization, acquiring the preprocessed data, and inputting the preprocessed data into a prediction model for training and testing, and outputting a prediction result according to a set path; the prediction result comprises a predicted value and an actual value, and the prediction model is a machine learning model. The method can improve the accuracy of prediction of the prediction model.

Images