Index trend space-time product probability predicting method based on time smooth filtering algorithm (TSFA) and artificial nerve network (ANN)

Abstract

An index trend space-time product probability predicting method based on a time smooth filtering algorithm (TSFA) and an artificial nerve network (ANN). The method includes first adopting the novel TSFA to preprocess an index to obtain a series of important high and low points to further obtain a plurality of important trends, then constructing time-space statistic parameters, namely the time-space-product, of the important trends, dividing the time-space product into a plurality of proper sections according to first-order back-direction difference of nonzero frequency to obtain time-space product probability of the sections, finally utilizing the AAN to fit the time-space product probability of the important trends to obtain the mapping relation of the time-space product and the probability. A security company can obtain the stopping probability value of the current important trends according to the mapping relation, so that an objective mathematical quantization tool based on data statistic analysis can be provided for investment decision. The important high and low points and medium-term high and low points of the index trends are distinguished, the finishing specific probability value of the current important trends can be provided for security analyzers, and the method has the advantages of being objective and accurate.

Description

technical field [0001] The invention relates to a method for predicting index trend time-space product probability based on TSFA and ANN. Background technique [0002] TSF——Time Smoothing Filtering Algorithm is the time smoothing filter algorithm. ANN——Artificial Neural Networks is artificial neural network. [0003] Since the birth of securities trading, securities forecasting has received extensive attention and active research, and various forecasting methods have emerged in an endless stream. With the popularity of high-performance computers, intelligent computing methods such as neural networks and genetic algorithms have also begun to be applied to stock index forecasting. However, most of the literature uses the generalization ability of artificial neural networks to predict the future position of the index by directly fitting the historical data of the stock index. According to the uncertainty theorem and chaos theory, due to the randomness of the object's motion,...

AI Technical Summary

Problems solved by technology

That is to say, if the artificial neural network is used to directly fit and predict the index, even if the predicted value with the highest probability of occurrence can indeed be obtained, the probability of occurrence of the predicted value cannot be given.

Images