Research On Stock Price Prediction Based On TDDPL-FWSVM-FWKNM

This paper investigates stock market indices prediction that is an interesting and important research in the areas of investment and applications,as it can get more profits and returns at lower risk rate with effective exchange strategies.To realize accurate prediction,various methods have been tried,among which the machine learning methods have drawn attention and been developed.In a basic hybridized framework of the feature weighted support vector machine as well as feature weighted K-nearest neighbor,this paper use a new hybridized framework of TDDPL(Trend Deterministic Data Preparation Layer)as well as the feature weighted support vector machine as well as feature weighted K-nearest neighbor to effectively predict stock market prices.Before modelling,we first use TDDPL(Trend Deterministic Data Preparation Layer)to process our feature data for getting discrete data.Secondly We establish a detailed theory of feature weighted SVM for the data classification assigning different weights for different features with respect to the classification importance.Then,to get the weights,we estimate the importance of each feature by computing the information gain.Lastly,we use feature weighted K-nearest neighbor to predict future stock market prices by computing k weighted nearest neighbors from the historical dataset.Compared with the basic hybridized framework,the new hybridized framework of TDDPL-FWSVM-FWKNN can achieve a better prediction capability to Shenzhen Stock Exchange Component Index and Shanghai Stock Exchange Composite Index in the short(5 day),medium(10 days)and long term(20 days)respectively with lower mean square error.