Self-adaptive financial time sequence prediction method based on k-line clustering and reinforcement learning

Abstract

The invention discloses a self-adaptive financial time sequence prediction method based on k-line clustering and reinforcement learning. The method comprises the following steps: firstly acquiring financial data, performing K linearization processing on the financial data, and computing the data after the K linearization processing, thereby obtaining the K line data in the current matching period;clustering various sub-components of the K line by using the Kmeans clustering algorithm, the FCM clustering algorithm or the online clustering method based on the data density; inputting the clustering result in the deep reinforcement learning model to perform the parameter training, and performing the financial transaction by using the trained deep reinforcement learning. The K-linearization isperformed on the financial data, and various sub-parts of the K line are clustered, the clustering result is input into the deep reinforcement learning model to obtain the deep reinforcement learningmodel based on the decomposing k-line clustering, and the online self-adaptive prediction of the real-time financial transaction price is realized.

Description

technical field [0001] The invention relates to the field of financial transactions, in particular to an adaptive financial time series prediction method based on decomposition k-line clustering and deep reinforcement learning. Background technique [0002] Realizing automated trading through computers is a common phenomenon in many developed countries. On the one hand, using computers to replace human transactions is because computers can find laws and phenomena that are difficult or impossible for people to capture from huge historical data. On the other hand, they can Greatly reduce the impact of traders' emotional fluctuations and avoid making irrational decisions in extreme market conditions. With the rapid development of artificial intelligence, it is the dream of every financial transaction and strategy researcher to train an automated trading model through artificial intelligence technology. Although many achievements have been made, it is not an easy task to direct...

AI Technical Summary

Problems solved by technology

Deng et al. applied fuzzy learning to price denoising. Through the fuzzification of prices, the noise can be removed to a certain extent, but the state space will be increased through fuzzification, and it is difficult to summarize the characteristics of the current market trend.

Images