Method for constructing prediction model based on improved whale optimization algorithm

Abstract

The invention provides a method for constructing a prediction model based on an improved whale optimization algorithm. The method comprises the following steps: obtaining sample data and carrying outnormalization processing on the obtained sample data; optimizing a penalty factor C and a kernel width gamma of the support vector machine by utilizing a cetyl optimization algorithm based on random permutation and a double-weight strategy; and on the basis of the obtained penalty factor C and the kernel width gamma, constructing a prediction model by using the normalized data, and classifying andpredicting the samples to be classified on the basis of the constructed prediction model. According to the implementation of the method, the penalty factor and the kernel width of the SVM are optimized by improving the whale optimization algorithm, the convergence speed and the convergence precision of the algorithm can be effectively improved, the capability of the algorithm to escape from a local optimal solution is improved, and a better global approximate optimal solution is found.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method for constructing a prediction model based on an improved gray whale optimization algorithm. Background technique [0002] Support Vector Machine (SVM) is often used to build a predictive model to analyze data, and the two most commonly used parameter optimization methods of Support Vector Machine (SVM) include grid search and gradient descent. In the first parameter optimization method, grid search is an exhaustive search method, which generally divides the specified parameter space by setting reasonable upper and lower limits of intervals and interval steps, and then analyzes the parameters represented by each grid node. Parameters are combined for training and prediction, and a set of parameters with the highest value in these prediction results is used as the best parameter of the final SVM model. Although this method can guarantee the optimal parameter combination...

AI Technical Summary

Problems solved by technology

In practical applications, if their values ​​are too large or too small, the generalization performance of SVM will deteriorate.

[0005] However, using the existing meta-heuristic search algorithm to deal with the SVM parameter optimization problem needs to further improve the convergence speed and convergence accuracy of the algorithm, and improve the ability of the algorithm to escape from the local optimal solution, so as to find a better global approximate optimal untie

Images