CAN DEEP MACHINE LEARNING OUTSMART THE MARKET? A COMPARISON BETWEEN ECONOMETRIC MODELLING AND LONG- SHORT TERM MEMORY

Using long-short term memory (LSTM) recurrent neural network (RNN) architecture, we analyse data from the Romanian stock markets in the attempt to forecast its future trend. Then we try to compare the results using the classical statistical modelling tools, further employing back testing to prove our findings. We believe that the LSTM should be the next tool in balancing portfolios and reducing market risk.

[1]  A. Craig MacKinlay,et al.  Stock Market Prices Do Not Follow Random Walks: Evidence from a Simple Specification Test , 1988 .

[2]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Kyong Joo Oh,et al.  Analyzing Stock Market Tick Data Using Piecewise Nonlinear Model , 2022 .

[5]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[8]  Stephen L Taylor,et al.  Modelling Financial Time Series , 1987 .

[9]  Razvan Pascanu,et al.  How to Construct Deep Recurrent Neural Networks , 2013, ICLR.

[10]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[11]  Morteza Esfandyari,et al.  Stock Market Index Prediction Using Artificial Neural Network , 2016 .

[12]  Soushan Wu,et al.  Comparison of support-vector machines and back propagation neural networks in forecasting the six major Asian stock markets , 2006 .

[13]  B. Malkiel.  The Efficient Market Hypothesis and Its Critics , 2003 .

[14]  T. Bollerslev,et al.  Modelling the Coherence in Short-run Nominal Exchange Rates: A Multivariate Generalized ARCH Model , 1990 .

[15]  Navdeep Jaitly,et al.  Towards End-To-End Speech Recognition with Recurrent Neural Networks , 2014, ICML.

[16]  An-Sing Chen,et al.  Application of Neural Networks to an Emerging Financial Market: Forecasting and Trading the Taiwan Stock Index , 2001, Comput. Oper. Res..

[17]  L. Novickytė,et al.  THE EFFICIENT MARKET HYPOTHESIS: A CRITICAL REVIEW OF LITERATURE AND METHODOLOGY , 2014 .

[18]  A. Lo,et al.  A Non-Random Walk Down Wall Street , 1999 .

[19]  A. Lo,et al.  Stock Market Prices Do Not Follow Random Walks: Evidence from a Simple Specification Test , 1987 .

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

[21]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[22]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[23]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[24]  Yvonne Herz,et al.  A Random Walk Down Wall Street The Time Tested Strategy For Successful Investing , 2016 .

[25]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[26]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[27]  D. Oprea,et al.  Informational Efficiency Tests on the Romanian Stock Market: A Review of the Literature , 2014 .

[28]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[29]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[30]  Yu Song,et al.  Application of artificial neural network for the prediction of stock market returns: The case of the Japanese stock market , 2016 .

[31]  Andrew Ang,et al.  Stock Return Predictability: Is it There? , 2001 .

[32]  Dr. Yasir Bin Tariq,et al.  The Efficient Market Hypothesis: A Critical Review of the Literature , 2016 .

[33]  L. Glosten,et al.  On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks , 1993 .

[34]  S RzepczynskiMark.  Neural Networks in Finance: Gaining Predictive Edge in the Markets (a review) , 2007 .

[35]  Razvan Pascanu,et al.  Theano: new features and speed improvements , 2012, ArXiv.

[36]  Timo Teräsvirta,et al.  An Introduction to Univariate GARCH Models , 2006 .

[37]  Snehanshu Saha,et al.  Predicting the direction of stock market prices using random forest , 2016, ArXiv.

[38]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[39]  Timothy Dozat,et al.  Incorporating Nesterov Momentum into Adam , 2016 .

[40]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[41]  R. Yaes.  The Efficient Market Hypothesis , 1989, Science.

[42]  Yudong Zhang,et al.  Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network , 2009, Expert Syst. Appl..

[43]  Kimon P. Valavanis,et al.  Surveying stock market forecasting techniques - Part II: Soft computing methods , 2009, Expert Syst. Appl..

[44]  Diego Klabjan,et al.  Classiffication-based Financial Markets Prediction using Deep Neural Networks , 2016, ArXiv.

[45]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.