Open AccessEscape Velocity backed avalanche predictor- Neural evidence from Nifty
Author(s) -
Bikramaditya Ghosh,
Emira Kozarević
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.d7104.118419
Subject(s) - proxy (statistics) , artificial neural network , econometrics , event (particle physics) , computer science , amplitude , artificial intelligence , statistical physics , economics , machine learning , physics , astrophysics , quantum mechanics
The concept of escape velocity has been extended from physics to stochastic finance and used as an avalanche predictor. Escape velocity being an extreme event serves as a perfect proxy of this stochastic finance event. This study identifies the propensity of the capital market to explode on rare occasions, which could be termed as avalanche. The frequency of such movement (both up and down) may not be high; however, the amplitude will be significantly high. The underlying for the study is Nifty, bellwether Indian bourse. Escape velocity has been calculated for Nifty on a daily basis for 17 years and prediction modelling has been constructed applying artificial neural networks (ANN) and multiple adaptive regression splines (MARS) simultaneously. Results indicate queer coupling of US events and Nifty apart from the evident behavioural traces. This research work is aimed at providing an implicit form of avalanche predictor from a distinctly different reference point.