Modeling method and device, storage medium and electronic equipment
A modeling method and modeling data technology, applied in the field of artificial intelligence, can solve problems such as poor prediction accuracy of artificial intelligence models, sudden changes in the trend of input variables, and deviations of indicators to be predicted.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] figure 1 It is a schematic flowchart of a modeling method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of creating a high-precision prediction model in the presence of data mutations. This method can be implemented by the modeling device provided by the embodiment of the present invention. For execution, the modeling device may be implemented by software and / or hardware, and the modeling device may be configured on an electronic computing device such as a computer or a server. The method specifically includes the following steps:
[0050] S110. Acquire historical data for modeling, where the historical data includes impact factors and result factors.
[0051] S120. Set a dummy variable and a variable value of the dummy variable based on the mutation of the outcome factor.
[0052] S130. Construct a prediction model based on the dummy variable, the impact factor, and the outcome factor.
[0053] The prediction model pred...
Embodiment 2
[0078] Figure 4 is an example flow diagram of a modeling method provided in Embodiment 2 of the present invention, which is optimized on the basis of the above embodiments. Optionally, based on the dummy variable, the impact factor and the result factor Before constructing the prediction model, the method further includes: preprocessing each of the impact factors based on the type of each of the impact factors. Specifically, the method does not include:
[0079] S210. Acquire historical data for modeling, where the historical data includes impact factors and result factors.
[0080] S220. Set a dummy variable and a variable value of the dummy variable based on the mutation of the outcome factor.
[0081] S230. Perform preprocessing on each of the impact factors based on the type of each of the impact factors.
[0082] S240. Construct a prediction model based on the dummy variable, the impact factor, and the outcome factor.
[0083] In this embodiment, due to the different...
Embodiment 3
[0088] Figure 5 It is a schematic flowchart of a modeling method provided by Embodiment 3 of the present invention, which is optimized on the basis of the above embodiments. Optionally, the method further includes: creating a stress scenario; under the stress scenario, based on The prediction model performs a prediction task to obtain a prediction result. The method specifically includes:
[0089] S310. Acquire historical data for modeling, where the historical data includes impact factors and result factors.
[0090] S320. Set a dummy variable and a variable value of the dummy variable based on the mutation of the outcome factor.
[0091] S330. Perform preprocessing on each of the impact factors based on the type of each of the impact factors.
[0092] S340. Construct a prediction model based on the dummy variable, the impact factor, and the outcome factor.
[0093] S350. Create a stress scenario. Under the stress scenario, perform a prediction task based on the predicti...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


