AI Paper Atlas

Research map / Time series / Foundation models for time series

Reasoning on Time-Series for Financial Technical Analysis

Kelvin J.L. Koa, Jan Chen, Yunshan Ma, Zheng Huanhuan, Tat-Seng Chua

ICLR 2026 · Time series › Foundation models for time series · approach: LLM-based time series forecasting · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
first RL fine-tuning (Time-GRPO) alone (ablation)base reasoning model · all dataMSE: 1.6% improvementImproved
add rejection sampling and SFT before second Time-GRPO RL (ablation)VTA reasoning model · all dataMSE: 20.3% average improvementImproved
condition reasoning on the forecasting model (joint conditional training) (ablation)VTA · all dataMSE/MAEImproved
remove technical indicators from reasoning (ablation)VTA · StockNetforecast errorHurt
add adversarial noise to indicator values (ablation)VTA · StockNetforecast errorNo clear effect
use verbal reasoning with inference-only LLMs instead of fine-tuned TransformerGPT-4.1 mini · All DataMSE: 2.6047 -> 0.2014Improved
add verbal reasoning to latent forecasting (VTA vs CALF)CALF · All DataMSE: 0.1235 -> 0.1178Improved
use VTA forecasts in Markowitz portfolioTimeLLM · PortfolioSharpe ratio: 1.5230 -> 1.7190Improved
apply VTA to ILI instead of financial dataVTA · ILIMSE: 1.0795 -> 1.4366Hurt
apply VTA to ETTh1CALF · ETTh1MSE: 0.0361 -> 0.0346Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy