Quantum hidden Markov stock prediction method and system, storage medium and terminal

Abstract

The invention discloses a quantum hidden Markov stock prediction method and system, a storage medium and a terminal. The method comprises the following steps: inputting the observation states of stocks arranged according to a time sequence in a certain period into a trained quantum hidden Markov model, and outputting the stock prediction data of different observation states at the next moment. Compared with the prior art in which the hidden Markov model is adopted to predict the stock data, the hidden Markov model of the quantum version is added into the stock prediction model, so that the credibility of the combination of the quantum algorithm and the classical algorithm can be verified; and under the condition that fewer parameters are used (two probability matrixes AC in the hidden Markov model are fused into a Karus operator, so that the use of the parameters is reduced), and the effect similar to that of a traditional hidden Markov model is achieved.

Description

technical field [0001] The invention relates to the field of quantum finance, in particular to a quantum hidden Markov stock prediction method, system, storage medium and terminal. Background technique [0002] Hidden Markov model, as an important concept in statistics, has been widely used in the financial field to establish a system-based model. As early as 1989, Hamilton proposed to use the system transition model to identify the economic cycle using the GNP sequence, and then Guidolin et al. It also extensively reviews applications of Markov switching models to empirical finance, including stock returns, the term structure of default-free interest rates, exchange rates, and the joint process of stock and bond returns. Outside of asset allocation, HMMs have been used to capture energy price dynamics (Dias and Ramos, 2014) to build credit risk systems, e.g. Petropoulos, Chatzis, and Xanthopoulos (2016) used students' HMMs to build credit rating systems. The results prove ...

AI Technical Summary

Problems solved by technology

[0006] Therefore, a quantum hidden Markov stock prediction method, system, storage medium and terminal are provided to solve the problem of too many parameters in the traditional hidden Markov algorithm in predicting the trend of the stock market, and the time and space when the amount of data is large. The two major problems with high complexity requirements belong to the problems that need to be solved urgently in this field

Images