Work detail

Forecasting stock market returns and volatility in different time horizons using Neural Networks

Author: Bc. Martin Hronec
Year: 2015 - summer
Leaders: doc. PhDr. Jozef Baruník Ph.D.
Consultants:
Work type: Bachelors
Language: English
Pages: 102
Awards and prizes:
Link: https://is.cuni.cz/webapps/zzp/detail/150416/
Abstract: This thesis is focused on multiple-step-ahead forecasting of Nasdaq Composite
index returns and daily range-based volatility. In order to capture the complex
patterns potentially hidden to traditional linear models we use artificial neural
networks as nonlinear, nonparametric and robust forecasting tool. We contribute
to the ongoing discussion about stock market predictability with following empirical
results. In case of Nasdaq Composite returns, all four applied neural networks
fail to outperform benchmark model in all time horizons, suggesting high unpredictability
in accordance with Efficient market hypothesis. Also in case of Nasdaq
Composite daily range-based volatility, 1 day and 1 month ahead predictions are
not significantly more accurate than benchmark model. However, we find 1-week
and 2-weeks-ahead forecasts to be significantly more accurate than benchmark
model and able to capture the predictive patterns.

Partners

Deloitte

Sponsors

CRIF
McKinsey
Patria Finance