Effective Fuzzy System for Qualifying the Characteristics of Stocks by Random Trading
This paper presents a fuzzy momentun contrarian uncertain characteristic system for the classification and quantification of stock characteristics.
Technology Overview
In this paper, a random trading algorithm using stop-loss and take-profit mechanisms for the extraction of stock characteristics is employed. The proposed FOCUS greatly improved classification performance, resulting in correlation coefficients of 0.572-0.722 with accuracy of 63.6%-84.5%.
Applications & Benefits
These results clearly demonstrate the efficacy of FOCUS in the quantification and classification of stocks suited to momentum- and contrarian-type trading strategies. In addition, the proposed FOCUS is applied to the real-world applications, and the FOCUS-selected outperforms the benchmark among all datasets, and increased the profitability by 1.5 times on TW50 dataset. These results demonstrate the effectiveness of the proposed FOCUS in the quantifying and classifying stocks as contrarian- or momentum-type and the real-world applications.
Abstract：
Trading strategies can be divided into two categories; i.e., those with momentum characteristic and those that appear contrarian. The characteristics of trading strategies have been widely studied; however, there has been relatively little work on the characteristics of stocks. Furthermore, there is no standard approach to the classification of stocks in terms of momentum and contrarian. This paper presents a fuzzy momentun contrarian uncertain characteristic system for the classification and quantification of stock characteristics. Random trading, stop-loss, and take-profit mechanisms are first used to identify characteristics, and then a novel profitability index with type-2 fuzzy-set module is used to quantify them. In the experiments, 41 stocks on the Taiwan 50 index were deemed suitable for momentum strategies, whereas 9 stocks were deemed suitable for contrarian strategies. An uphill relationship between profitability index and trading performance is observed, which produced correlation coefficients of 0.148--0.539, and classification accuracy of 52.0\%--60.0\%. However, the proposed system greatly improved classification performance, resulting in correlation coefficients of 0.572--0.722 with accuracy of 63.6\%--84.5\%. In the real-world application, the proposed system outperforms the benchmark among all datasets, and increases the profitability by 1.5 times on Taiwan 50 dataset. hese results clearly demonstrate the efficiency of the proposed system}in the quantification and classification of stocks suited to momentum- and contrarian-type trading strategies and also in the real-world applications.
Effective Fuzzy System for Qualifying the Characteristics of Stocks by Random Trading
Author：Wu M., Syu J., Lin J.C., Ho J.
Year：2021
Source publication：IEEE Transactions on Fuzzy Systems, Volume: 30, Issue: 8
Subfield Highest percentage：99% Control and Systems Engineering #2/260