Title: Extreme value theory and neural network for catastrophic fall prediction: a study of year 2008-2009
Authors: Utkarsh Shrivastava; Gyan Prakash; Joydip Dhar
Addresses: School of Management, Lovely Professional University, Flat-804(A), Block 41-D2, LPU, Phagwara, Punjah, 144411, India ' Department of Management, ABV-Indian Institute of Information Technology and Management, Gwalior-474001, Block-E, Room No. 116, ABV-IIITM, Gwalior, 474010, India ' Department of Applied Science, ABV-Indian Institute of Information Technology and Management, Gwalior-474001, Block-E, Room No. 116, ABV-IIITM, Gwalior – 474010, India
Abstract: Extreme value theory to a certain extent is successful in modelling extreme events as it assumes that outliers follow distribution other than normal. However, a mathematical model might not just be sufficient to predict extreme events. Nowadays, extreme events have become so common that investors' past experience of such situations takes over and plays important role in guiding collective behaviour during downturn. In this study, firstly extreme events are modelled using generalised extreme value (GEV) distribution. Secondly, past deviations from return levels obtained as quantile of GEV distribution and future risk of market falling below the same level are classified using perceptron network. Neural network is basically used to inculcate learning form past market movements to predict future. Trained network hence obtained is used for simulating monthly risk for catastrophic years 2008 and 2009. Comparison of actual and forecasted results indicates substantial improvement in market fall prediction.
Keywords: extreme value theory; EVT; perceptron networks; 2008 recession; return levels; Frechet type distribution; stock market crash; neural networks; catastrophic falls; market fall prediction; modelling; extreme events; market movements; past movements; forecasting; simulation.
International Journal of Information and Decision Sciences, 2014 Vol.6 No.2, pp.193 - 210
Available online: 28 May 2014 *Full-text access for editors Access for subscribers Purchase this article Comment on this article