A spectral relevance analysis approach to pattern recognition of financial time series
- Understanding patterns in financial time series is crucial for improving prediction accuracy in algorithmic trading and risk management. This paper presents a novel AI-based computer vision approach for classifying financial time series. Historical price sequences are transformed into Gramian Angular Difference Field (GADF) images and fed into a convolutional neural network (CNN) for pattern recognition. To interpret the CNN’s decision-making process, we apply Spectral Relevance Analysis (SpRAy), enabling the identification of distinct clusters based on relevance maps. Clustering the images according to their relevance profiles reveals groups with significantly higher predictive performance compared to the full dataset. The corresponding relevance patterns highlight favorable price movement structures and are identified via the associated clusters.
Download full text files
Statistics
Print On Demand
Additional Services
| Author: | Christine Distler, Yarema OkhrinORCiDGND, Jonathan PfahlerORCiDGND |
|---|---|
| URN: | urn:nbn:de:bvb:384-opus4-1253113 |
| Frontdoor URL | https://opus.bibliothek.uni-augsburg.de/opus4/125311 |
| ISSN: | 0957-4174OPAC |
| Parent Title (English): | Expert Systems with Applications |
| Publisher: | Elsevier BV |
| Place of publication: | Amsterdam |
| Type: | Article |
| Language: | English |
| Year of first Publication: | 2026 |
| Publishing Institution: | Universität Augsburg |
| Release Date: | 2025/09/20 |
| Volume: | 298 |
| Issue: | part A |
| First Page: | 129555 |
| DOI: | https://doi.org/10.1016/j.eswa.2025.129555 |
| Institutes: | Wirtschaftswissenschaftliche Fakultät |
| Wirtschaftswissenschaftliche Fakultät / Institut für Statistik und mathematische Wirtschaftstheorie | |
| Wirtschaftswissenschaftliche Fakultät / Institut für Statistik und mathematische Wirtschaftstheorie / Lehrstuhl für Statistik | |
| Dewey Decimal Classification: | 3 Sozialwissenschaften / 33 Wirtschaft / 330 Wirtschaft |
| Licence (German): |  CC-BY 4.0: Creative Commons: Namensnennung (mit Print on Demand) |
