Not logged in.
Quick Search - Contribution
Contribution Details
| Type | Master's Thesis |
| Scope | Discipline-based scholarship |
| Title | Recognizing Technical Patterns with Images |
| Organization Unit | |
| Authors |
|
| Supervisors |
|
| Language |
|
| Institution | University of Zurich |
| Faculty | Faculty of Business, Economics and Informatics |
| Number of Pages | 46 |
| Date | 2022 |
| Abstract Text | We reconsider the technical analysis using the image recognition method, exploring asset price behavior after some popular technical patterns. Comparing the results from the image recognition model to the rule-based method with time series, we find that the image recognition model can detect much more patterns than the rule-based one. In the event study, we show there are significant cumulative abnormal returns after most of these technical patterns with various holding periods. We construct a portfolio based on these patterns and show this trading strategy can achieve significant excess returns and high Sharpe ratio. This result is robust and cannot be captured by the Fama-French factors. |
| Export |
BibTeX
|