Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Faculty of Business | en_US |
| dc.contributor.advisor | Wei, Steven (AF) | en_US |
| dc.creator | Cheung, Yee Chung | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/13857 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Trade with AI pattern recognition | en_US |
| dcterms.abstract | Price patterns and technical indicators are pivotal tools in technical analysis, guiding trading decisions such as entry points, stop-loss levels, and profit targets. However, accurately identifying these patterns remains challenging, often relying on traders’ expertise and manual efforts. This study introduces a novel one-shot candlestick price pattern recognition system leveraging computer vision to enhance efficiency and accuracy in financial markets. | en_US |
| dcterms.abstract | We propose the CandSiNet model, a Siamese network architecture with a CNN backbone, representing the first application of one-shot classification to candlestick price patterns. Two key innovations underpin this work: (1) the use of Gramian Angular Summation Field (GASF) and Gramian Angular Difference Field (GADF) techniques to transform time series data into feature-rich images, and (2) a time-shifted resampling method to address data scarcity issues during training. Experiments confirm that the CandSiNet model successfully achieves accurate one-shot classification, highlighting its robustness and practical utility in technical analysis. | en_US |
| dcterms.abstract | This study contributes to the emerging field of applying computer vision to financial modeling, offering a framework for future exploration of technical pattern classification. By automating the recognition of intricate price patterns, our findings empower traders to enhance decision-making, risk assessment, and profitability in dynamic financial markets. | en_US |
| dcterms.extent | 228 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2025 | en_US |
| dcterms.educationalLevel | DFinTech | en_US |
| dcterms.educationalLevel | All Doctorate | en_US |
| dcterms.LCSH | Investments | en_US |
| dcterms.LCSH | Investment analysis | en_US |
| dcterms.LCSH | Artificial intelligence | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8375.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 2.91 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/13857