LSTM-Based Quantitative Trading Using Dynamic K-Top and Kelly Criterion

With the strong capability of modeling time sequence, long short-term memory (LSTM) networks have been widely applied to predicting financial time series. This has attracted tremendous attention in the quantitative trading area. A complete quantitative trading system usually has three tasks, including market timing, stock selection, and portfolio management. In this paper, we present an LSTM-based quantitative trading system and optimize this system from the following two aspects. Firstly, in the process of stock selection, we first introduce the dynamic K-top method in the LSTM-based quantitative trading system to follow the market change. Secondly, concerning portfolio management, we further incorporate the Kelly Criterion to attain an appropriate position ratio. Taking CSI300 constituent stocks as the study example, extensive experiments have been carried out to show the superiority of the proposed method. In comparison with the straight forward LSTM-based trading strategy, the improved LSTM-based trading strategy with the dynamic K-top method and the Kelly Criterion can achieve an increase of 44.97% over ten days in terms of accumulative return. In addition, our novel method can gain a win ratio of 55.95%, a monthly alpha of 0.16, a monthly Sharpe ratio of 2.17, and a monthly Sortino ratio of 2.96 disregarding the transaction costs.

[1]  Svetlana Borovkova,et al.  An Ensemble of LSTM Neural Networks for High-Frequency Stock Market Classification , 2018, Journal of Forecasting.

[2]  Yuan Song.  Stock Trend Prediction: Based on Machine Learning Methods , 2018 .

[3]  Satit Yodmun,et al.  Stock Selection into Portfolio by Fuzzy Quantitative Analysis and Fuzzy Multicriteria Decision Making , 2016, Adv. Oper. Res..

[4]  Maureen O'Hara,et al.  Market Statistics and Technical Analysis: The Role of Volume , 1994 .

[5]  Ling Tang,et al.  A novel hybrid stock selection method with stock prediction , 2019, Appl. Soft Comput..

[6]  Kelly criterion revisited: optimal bets , 2006, physics/0607166.

[7]  Xiaodan Liang,et al.  LSTM with Wavelet Transform Based Data Preprocessing for Stock Price Prediction , 2019, Mathematical Problems in Engineering.

[8]  F. Tay,et al.  Application of support vector machines in financial time series forecasting , 2001 .

[9]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[10]  R. Thaler,et al.  Does the Stock Market Overreact , 1985 .

[11]  André F. Perold,et al.  Large-Scale Portfolio Optimization , 1984 .

[12]  Siyuan Liu,et al.  Stock transaction prediction modeling and analysis based on LSTM , 2018, 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[13]  William T. Ziemba,et al.  Good and Bad Properties of the Kelly Criterion , 2003 .

[14]  Gholam R. Amin,et al.  Modelling stock selection using ordered weighted averaging operator , 2018, Int. J. Intell. Syst..

[15]  Akbar Siami Namin,et al.  Forecasting Economics and Financial Time Series: ARIMA vs. LSTM , 2018, ArXiv.

[16]  Chien-Feng Huang,et al.  A hybrid stock selection model using genetic algorithms and support vector regression , 2012, Appl. Soft Comput..

[17]  Ian G. McHale,et al.  Optimal Betting Under Parameter Uncertainty: Improving the Kelly Criterion , 2013, Decis. Anal..

[18]  Wu Meng,et al.  Application of Support Vector Machines in Financial Time Series Forecasting , 2007 .

[19]  Adriano C. M. Pereira,et al.  Stock market's price movement prediction with LSTM neural networks , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[20]  Ratchata Peachavanish,et al.  Stock Selection and Trading Based on Cluster Analysis of Trend and Momentum Indicators , 2022 .

[21]  Narasimhan Jegadeesh,et al.  Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency , 1993 .

[22]  Thomas Fischer,et al.  Deep learning with long short-term memory networks for financial market predictions , 2017, Eur. J. Oper. Res..

[23]  Akbar Siami Namin,et al.  A Comparison of ARIMA and LSTM in Forecasting Time Series , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[24]  Hong Peng,et al.  High-Frequency Stock Trend Forecast Using LSTM Model , 2018, 2018 13th International Conference on Computer Science & Education (ICCSE).

[25]  Ammar Belatreche,et al.  Evaluating machine learning classification for financial trading: An empirical approach , 2016, Expert Syst. Appl..

[26]  Robert B. Litterman,et al.  Global Portfolio Optimization , 1992 .

[27]  Tao Dong,et al.  A Machine Learning Framework for Stock Selection , 2018, ArXiv.

[28]  Ling Tang,et al.  Stock Selection with a Novel Sigmoid-Based Mixed Discrete-Continuous Differential Evolution Algorithm , 2016, IEEE Transactions on Knowledge and Data Engineering.

[29]  Jian Cao,et al.  Financial time series forecasting model based on CEEMDAN and LSTM , 2019, Physica A: Statistical Mechanics and its Applications.