Stock prediction method for optimizing deep belief network based on improved chimpanzee algorithm

Abstract

The invention discloses a stock prediction method for optimizing a deep belief network based on an improved chimpanzee algorithm. The method is characterized by comprising the following steps: S1, inputting stock data into a DBN network, wherein the structure of the initial network includes the number of hidden layers of the network, the number of neurons of each layer, a learning rate, and the number of batch processing samples, and training the sample data; and S2, selecting an average percentage error (MAPE) of a predicted value output by the DBN model as an optimization objective function. A chimpanzee optimization algorithm is used to optimize the learning rate of the DBN and batch processing sample number parameters, and network performance instability caused by parameter setting through human experience is avoided, so that an optimal parameter combination is obtained, and the prediction performance of the DBN model for different stock data is improved.

Description

technical field [0001] The invention relates to the technical field of parameter optimization of a deep belief network DBN, in particular to a stock prediction method based on an improved chimpanzee algorithm to optimize a deep belief network. Background technique [0002] As a deep network, DBN is stacked by Restricted Boltzmann Machine (RBM), that is, the output of the previous layer of RBM is the input of the next layer of RBM. As a typical multi-layer network, it has good feature extraction and nonlinear fitting capabilities. However, in the construction process of the DBN network, artificial experience is often used to manually adjust the parameters of the network, such as the learning rate, the number of samples processed each time (BS, Batch Size), etc. The increase of the learning rate can improve the training speed of the network, but it is easy to cause the network to fall into a local minimum or non-convergence. The size of BS affects the degree of optimization ...

AI Technical Summary

Problems solved by technology

In addition, the prey obtained during the hunting process of chimpanzees will be exchanged for certain social benefits. This invisible reward mechanism will prompt them to forget their responsibilities during the hunting process, that is, not to chase the prey temporarily. This behavior will increase the convergence rate in the optimization algorithm and avoid Trapped in a local optimal solution, in order to solve the structural instability and randomness caused by inappropriate parameters of the deep belief network DBN in the stock market prediction, the present invention proposes a stock market prediction method based on swarm intelligence chimpanzee optimization DBN

Images