Research Online

Logo

Goldsmiths - University of London

Sentiment and stock market volatility predictive modelling - A hybrid approach

Olaniyan, Rapheal; Stamate, Daniel; Ouarbya, Lahcen and Logofatu, Doina. 2015. 'Sentiment and stock market volatility predictive modelling - A hybrid approach'. In: 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA). Paris, France. [Conference or Workshop Item]

[img]
Preview
Text
DSAA.pdf

Download (312kB) | Preview

Abstract or Description

The frequent ups and downs are characteristic to the stock market. The conventional standard models that assume that investors act rationally have not been able to capture the irregularities in the stock market patterns for years. As a result, behavioural finance is embraced to attempt to correct these model shortcomings by adding some factors to capture sentimental contagion which may be at play in determining the stock market. This paper assesses the predictive influence of sentiment on the stock market returns by using a non-parametric nonlinear approach that corrects specific limitations encountered in previous related work. In addition, the paper proposes a new approach to developing stock market volatility predictive models by incorporating a hybrid GARCH and artificial neural network framework, and proves the advantage of this framework over a GARCH only based framework. Our results reveal also that past volatility and positive sentiment appear to have strong predictive power over future volatility.

Item Type:

Conference or Workshop Item (Paper)

Identification Number (DOI):

https://doi.org/10.1109/DSAA.2015.7344855

Keywords:

Granger causality, non-parametric test, GARCH, EGARCH, artificial neural networks, sentiment, stock market, volatility, Monte Carlo simulations

Departments, Centres and Research Units:

Computing

Dates:

DateEvent
19 November 2015Published
22 July 2015Accepted

Event Location:

Paris, France

Item ID:

17664

Date Deposited:

05 Apr 2016 07:30

Last Modified:

17 May 2019 09:49

URI:

http://research.gold.ac.uk/id/eprint/17664

View statistics for this item...

Edit Record Edit Record (login required)