Abstract
Nowadays, machine trading contributes significantly to activities in the equity market, and forecasting market movement under high-frequency scenario has become an important topic in finance. A key challenge in high-frequency market forecasting is modeling the dependency structure among stocks and business sectors, with their high dimensionality and the requirement of computational efficiency. As a group of powerful models, neural networks (NNs) have been used to capture the complex structure in many studies. However, most existing applications of NNs only focus on forecasting with daily or monthly data, not with minute-level data that usually contains more noises. In this article, we propose a novel double-layer neural (DNN) network for high-frequency forecasting, with links specially designed to capture dependence structures among stock returns within different business sectors. Various important technical indicators are also included at different layers of the DNN framework. Our model framework allows update over time to achieve the best goodness-of-fit with the most recent data. The model performance is tested based on 100 stocks with the largest capitals from the S8P 500. The results show that the proposed framework outperforms benchmark methods in terms of the prediction accuracy and returns. Our method will help in financial analysis and trading strategy designs.
- Torben G. Andersen, Tim Bollerslev, and Francis X. Diebold. 2007. Roughing it up: Including jump components in the measurement, modeling, and forecasting of return volatility. Rev. Econom. Stat. 89, 4, 701--720. Google ScholarCross Ref
- Torben G. Andersen, Tim Bollerslev, Francis X. Diebold, and Heiko Ebens. 2001. The distribution of realized stock return volatility. J. Finan. Econ. 61, 1, 43--76. Google ScholarCross Ref
- Andrés Arévalo, Jaime Niño, German Hernández, and Javier Sandoval. 2016. High-frequency trading strategy based on deep neural networks. In Intelligent Computing Methodologies. Springer International Publishing, 424--436.Google Scholar
- Senthil Arasu Balasubramanian, Jeevananthan Manickavasagam, Thamaraiselvan Natarajan, and Janarthanan Balakrishnan. 2015. An experimental analysis of forecasting the high frequency data of matured and emerging economies stock index using data mining techniques. Int. J. Operat. Res. 23, 4, 406--426. Google ScholarCross Ref
- G. W. Brown and M. T. Cliff. 2004. Investor sentiment and the near-term stock market. J. Empir. Finance. 11, 1, 1--27. Google ScholarCross Ref
- Pei-Chann Chang, Di-di Wang, and Chang-le Zhou. 2012. A novel model by evolving partially connected neural network for stock price trend forecasting. Expert Syst. Applic. 39, 1, 611--620. Google ScholarDigital Library
- Gong-meng Chen, Michael Firth, and Oliver M. Rui. 2001. The dynamic relation between stock returns, trading volume, and volatility. Finan. Rev. 36, 3, 153--174. Google ScholarCross Ref
- Tai-Liang Chen, Ching-Hsue Cheng, and Hia Jong Teoh. 2007. Fuzzy time-series based on Fibonacci sequence for stock price forecasting. Phys. A: Stat. Mech. Applic. 380, 377--390. Google ScholarCross Ref
- Thomas C. Chiang, Hai-Chin Yu, and Ming-Chya Wu. 2009. Statistical properties, dynamic conditional correlation, scaling analysis of high-frequency intraday stock returns: Evidence from dow-jones and nasdaq indices. Phys. A. 388, 8, 1555--1570. Google ScholarCross Ref
- Taufiq Choudhry, Frank McGroarty, Ke Peng, and Shiyun Wang. 2012. High-frequency exchange-rate prediction with an artificial neural network. Intell. Syst. Account., Finan. Manage. 19, 3, 170--178.Google ScholarDigital Library
- Wensheng Dai, Jui-Yu Wu, and Chi-Jie Lu. 2012. Combining nonlinear independent component analysis and neural network for the prediction of Asian stock market indexes. Expert Syst. Applic. 39, 4, 4444--4452. Google ScholarDigital Library
- Philip Hans Franses and Dick Van Dijk. 1996. Forecasting stock market volatility using (nonlinear) GARCH models. J. Forecast. 229--235. Google ScholarCross Ref
- M. Ghiassi, J. Skinner, and D. Zimbra. 2013. Twitter brand sentiment analysis: A hybrid system using n-gram analysis and dynamic artificial neural network. Expert Syst. Applic.: An Int. J. 40, 16, 6266--6282. Google ScholarDigital Library
- Rosella Giacometti, Marida Bertocchi, Svetlozar T. Rachev, and Frank J. Fabozzi. 2012. A comparison of the Lee-Carter model and AR-ARCH model for forecasting mortality rates. Insurance: Math. Econom. 50, 1, 85--93 Google ScholarCross Ref
- M. D. Rafiul Hassan, Baikunth Nath, and Michael Kirley. 2007. A fusion model of HMM, ANN and GA for stock market forecasting. Expert Syst. Applic. 33, 1, 171--180. Google ScholarDigital Library
- C. C. Holt. 2004. Author's retrospective on ‘forecasting seasonals and trends by exponentially weighted moving averages. Int. J. Forecast. 20, 1, 11--13. DOI:10.1016/j.ijforecast.2003.09.017. Google ScholarCross Ref
- Sheng-Hsun Hsu, J. J. Po-An Hsieh, Ting-Chih Chih, and Kuei-Chu Hsu. 2009. A two-stage architecture for stock price forecasting by integrating self-organizing map and support vector regression. Expert Syst. Applic. 36, 4, 7947--7951. Google ScholarDigital Library
- Roger D. Huang and Hans R. Stoll. 1994. Market microstructure and stock return predictions. Rev. Finan Stud. 7, 1, 179--213. Google ScholarCross Ref
- Yakup Kara, Melek Acar Boyacioglu, and Ömer Kaan Baykan. 2011. Predicting direction of stock price index movement using artificial neural networks and support vector machines: The sample of the istanbul stock exchange. Expert Syst. Applic. 38, 5, 5311--5319. Google ScholarDigital Library
- Jonathan M. Karpoff. 1987. The relation between price changes and trading volume: A survey. J. Finan. and Quantitat. Anal. 22, 01, 109--126. Google ScholarCross Ref
- Bryan Kelly and Seth Pruitt. 2015. The three-pass regression filter: A new approach to forecasting using many predictors. J. Econometrics. 186, 2, 294--316. Google ScholarCross Ref
- Christopher G. Lamoureux and William D. Lastrapes. 1990. Heteroskedasticity in stock return data: volume versus GARCH effects. J. Finance 45, 1, 221--229. Google ScholarCross Ref
- Fajiang Liu and Jun Wang. 2012. Fluctuation prediction of stock market index by Legendre neural network with random time strength function. Neurocomputing 83, 12--21. Google ScholarDigital Library
- Ping-Feng Pai and Chih-Sheng Lin. 2005. A hybrid ARIMA and support vector machines model in stock price forecasting. Omega 33, 6. 497--505.Google ScholarCross Ref
- Jigar Patel, Sahil Shah, Priyank Thakkar, and K. Kotecha. 2015. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Syst. Applicat. 42, 1, 259--268. Google ScholarDigital Library
- Alexis Akira Toda. 2012. The double power law in income distribution: Explanations and evidence. J. Econom. Behav. Organ. 84, 1, 364--381. Google ScholarCross Ref
- Alexis Akira Toda and Kieran James Walsh. 2014. The double power law in consumption and implications for testing euler equations. Available at SSRN 2319454.Google Scholar
- Chih-Fong Tsai and Yu-Chieh Hsiao. 2010. Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches. Decis. Supp. Syst. 50, 1, 258--269. Google ScholarDigital Library
- Johannes Voit. 2013. The Statistical Mechanics of Financial Markets: Springer Science 8 Business Media.Google Scholar
- Martin L. Weitzman. 2007. Subjective expectations and asset-return puzzles. Amer. Econom. Rev.:1102--1130.Google Scholar
- J. Zakon and J. C. Pennypacker. 1968. An analysis of the advance-decline line as a stock market indicator. J. Finan. Quant. Anals. 3, 3, 299--314 Google ScholarCross Ref
Index Terms
- A Double-Layer Neural Network Framework for High-Frequency Forecasting
Recommendations
Hybrid ARMA-GARCH-Neural Networks for intraday strategy exploration in high-frequency trading
Highlights- This study examines the potential impact of global geopolitical events on the stock market prices of the Dow Jones U.S. Aerospace & Defense Index, as well as fluctuations in FOREX markets such as the British pound and Chinese renminbi.
AbstractThe frequency of armed conflicts increased during the last 20 years. The problems of the emergence of military disputes, not only concern social parameters, but also economic and financial dimensions. This study examines the potential impact of ...
Regression neural network for error correction in foreign exchange forecasting and trading
Predicting exchange rates has long been a concern in international finance as most standard econometric methods are unable to produce significantly better forecasts than the random walk model. Recent studies provide some evidence for the ability of ...
Using neural network for forecasting TXO price under different volatility models
This study applies backpropagation neural network for forecasting TXO price under different volatility models, including historical volatility, implied volatility, deterministic volatility function, GARCH and GM-GARCH models. The sample period runs from ...
Comments