A new automatic forecasting method based on explainable deep dendritic artificial neural network
Eren Bas, Erol Egrioglu · 2025
Read A new automatic forecasting method based on explainable deep dendritic artificial neural network by Eren Bas, Erol Egrioglu (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12748647.txt.
Description
Eren Bas and Erol Egrioglu present a 2025 paper on forecasting that runs itself and can explain its choices. Practitioners dislike methods that demand subjective tuning at every step. The authors build their automation around a deep dendritic recurrent network, a brain-inspired model whose inputs can be tested one by one for real significance.
Significance tests decide which inputs enter the model, and validity tests check the fitted result, all framed as explainability tools. Simulations probed how well the tests behave. The full automatic method then faced famous forecasting rivals on the M3 and M4 competition series, thousands of real-world tracks from business and economics. The authors report a method that needs no hand-holding yet keeps its reasoning visible. Automation plus audit trails is the pitch.
Catalog record
| CREATOR | Eren Bas, Erol Egrioglu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 90 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |