KAN vs LSTM Performance in Time Series Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908671098748928 |
|---|---|
| author | Rather, Tabish Ali Joy, S M Mahmudul Hasan Sukhorukova, Nadezda Frascoli, Federico |
| author_facet | Rather, Tabish Ali Joy, S M Mahmudul Hasan Sukhorukova, Nadezda Frascoli, Federico |
| contents | This paper compares Kolmogorov-Arnold Networks (KAN) and Long Short-Term Memory networks (LSTM) for forecasting non-deterministic stock price data, evaluating predictive accuracy versus interpretability trade-offs using Root Mean Square Error (RMSE).LSTM demonstrates substantial superiority across all tested prediction horizons, confirming their established effectiveness for sequential data modelling. Standard KAN, while offering theoretical interpretability through the Kolmogorov-Arnold representation theorem, exhibits significantly higher error rates and limited practical applicability for time series forecasting. The results confirm LSTM dominance in accuracy-critical time series applications while identifying computational efficiency as KANs' primary advantage in resource-constrained scenarios where accuracy requirements are less stringent. The findings support LSTM adoption for practical financial forecasting while suggesting that continued research into specialised KAN architectures may yield future improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_18613 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KAN vs LSTM Performance in Time Series Forecasting Rather, Tabish Ali Joy, S M Mahmudul Hasan Sukhorukova, Nadezda Frascoli, Federico Machine Learning Artificial Intelligence 92B20, 68T07 I.2.6; G.3; I.5.1 This paper compares Kolmogorov-Arnold Networks (KAN) and Long Short-Term Memory networks (LSTM) for forecasting non-deterministic stock price data, evaluating predictive accuracy versus interpretability trade-offs using Root Mean Square Error (RMSE).LSTM demonstrates substantial superiority across all tested prediction horizons, confirming their established effectiveness for sequential data modelling. Standard KAN, while offering theoretical interpretability through the Kolmogorov-Arnold representation theorem, exhibits significantly higher error rates and limited practical applicability for time series forecasting. The results confirm LSTM dominance in accuracy-critical time series applications while identifying computational efficiency as KANs' primary advantage in resource-constrained scenarios where accuracy requirements are less stringent. The findings support LSTM adoption for practical financial forecasting while suggesting that continued research into specialised KAN architectures may yield future improvements. |
| title | KAN vs LSTM Performance in Time Series Forecasting |
| topic | Machine Learning Artificial Intelligence 92B20, 68T07 I.2.6; G.3; I.5.1 |
| url | https://arxiv.org/abs/2511.18613 |