Open AccessEmpirical Analysis of Stock Investment Based on β-KFCM
Author(s) -
Yuxue Wang,
Zongxiang Song,
Xiaoping Ren
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1624/2/022050
Subject(s) - cluster analysis , data mining , fuzzy clustering , empirical research , econometrics , stock market , fuzzy logic , computer science , actuarial science , mathematics , artificial intelligence , economics , statistics , paleontology , horse , biology
Cluster analysis is an analysis method that classifies data sets. It measure the similarity between different data and classifies them on the basis of similarity, but the classification is unknown. In recent years, with the popularization and improvement of information technology, a large number of diversified data have been produced in various industries. In order to extract data features and classify them, this paper, based on the study of fuzzy C-means clustering algorithm, take the systematic risk coefficient as the weight, expand the model to get the weighted fuzzy kernel clustering algorithm: -KFCM fuzzy clustering algorithm and solve the algorithm. Based on the empirical research, we choose six Accounting Indicators to study 50 stocks in A-share market, including current ratio, cash ratio, year-on-year growth rate of operating revenue, return rate of total assets, net sales interest rate and asset liability ratio. According to the empirical research, we can get the results that the investment grade is divided into three categories, among them, Category I is the recommended high-quality investment variety, category II and category III are next to it.