pith:KWFGFRC4
Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking
Echo state networks match ARIMA and TBATS accuracy on monthly series and beat them on quarterly series at lower computational cost.
arxiv:2602.03912 v4 · 2026-02-03 · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KWFGFRC4ICI4U4CGS2UJMOND2I}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Across both frequencies, the ESN performs on par with ARIMA and TBATS for monthly data and achieves the lowest mean MASE for quarterly data, while requiring lower computational cost than ARIMA and TBATS.
That the hyperparameter configurations found optimal on the Parameter dataset will generalize without further tuning to the disjoint Forecast dataset and that the chosen M4 subset is representative enough for the claimed practical advantage.
Echo State Networks match or beat ARIMA and TBATS on quarterly M4 series and match them on monthly series while using less compute after an extensive hyperparameter sweep.
Formal links
Receipt and verification
| First computed | 2026-06-02T01:03:42.348147Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
558a62c45c4091ca704696a89639a3d20c4c72840413fb19daf0c849c5f1495c
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KWFGFRC4ICI4U4CGS2UJMOND2I \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 558a62c45c4091ca704696a89639a3d20c4c72840413fb19daf0c849c5f1495c
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "e31ad758df7854d245356b889812f5433c678784c5280ae0fc658a8ad679247c",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-02-03T16:01:22Z",
"title_canon_sha256": "9934e48f829fe1391f9d7fa6b3d374e344198f3d961c39774d08509fe111b6af"
},
"schema_version": "1.0",
"source": {
"id": "2602.03912",
"kind": "arxiv",
"version": 4
}
}