Predicting Stock Market Volatility with Google Trends
| Název práce v češtině: | Předpověď volatility akcií s pomocí Google trends |
|---|---|
| Název v anglickém jazyce: | Predicting Stock Market Volatility with Google Trends |
| Klíčová slova: | Google trends, finanční trhy, volatilita |
| Klíčová slova anglicky: | google trends, financial markets, volatility |
| Akademický rok vypsání: | 2014/2015 |
| Typ práce: | bakalářská práce |
| Jazyk práce: | angličtina |
| Ústav: | Institut ekonomických studií (23-IES) |
| Vedoucí / školitel: | prof. PhDr. Ladislav Krištoufek, Ph.D. |
| Řešitel: | skrytý - zadáno vedoucím/školitelem |
| Datum přihlášení: | 17.06.2015 |
| Datum zadání: | 17.06.2015 |
| Datum a čas obhajoby: | 06.09.2016 00:00 |
| Místo konání obhajoby: | IES |
| Datum odevzdání elektronické podoby: | 29.07.2016 |
| Datum proběhlé obhajoby: | 06.09.2016 |
| Oponenti: | Mgr. Bc. Tomáš Janotík |
| Kontrola URKUND: | |
| Zásady pro vypracování |
| Methodology
To examine my hypotheses, I will improve on a standard volatility model (e.g. HAR (Corsi2009) or GARCH (Bollerslev1986) or both) by adding Google data search queries for particular stocks. In the case of HAR, I will use the common open-close-high-low Garman & Klass estimator. Further on, I will analyse the models with or without Google data both in-sample and out-of- sample and compare with the DM test (Diebold1995,Diebold2013). Outline 1. Introduction 2. Literature Review & Theoretical Background 3. Methodology 4. Empirical Model 5. Discussion of Results 6. Conclusion |
| Seznam odborné literatury |
| Corsi, F. (2009): A Simple Approximate Long Memory Model of Realized Volatility, Journal of Financial Econometrics 7 (2), pp. 174-196
Dimpfl, T., Jank, S. (2015): Can internet search queries help to predict stock market volatility? European Financial Management, Forthcoming Ramos, S. B., Veiga, H., Latoeiro, P. (2013): Predictability of stock market activity using Google search queries, Statistics and Econometrics Working Papers, ws130605 |
| Předběžná náplň práce |
| TBD |
| Předběžná náplň práce v anglickém jazyce |
| Search query data is an emerging area in economic studies. Since the Google's launch of the Google Insights in 2008, one of the first observed and implemented models was used for predicting the incidence of influenza-like diseases with less time lag than official indicators. Later on, as query indices proved to be correlated with diverse economic indicators, many studies examining search data in various economic fields have emerged.
Among these economic fields I will aim at the application of Google search volume data on the interdependence between search and volatility of the financial market. Specifically, I will focus on the improvement of volatility models by adding Google search queries data into them. To examine my hypotheses, I will improve on a standard volatility model (e.g. HAR (Corsi2009) or GARCH (Bollerslev1986) or both) by adding Google data search queries for particular stocks. In the case of HAR, I will use the common open-close-high-low Garman & Klass estimator. Further on, I will analyse the models with or without Google data both in-sample and out-of-sample and compare with the DM test (Diebold1995,Diebold2013). |