Abstract:We introduce Semantic State Abstraction Interfaces (SSAI): a methodological template for mapping sparse unstructured text into $K$ auditable, named coordinates with neutral defaults on no-news days, designed to separate representation hypotheses from optimisation variance in sequential decision systems. Our contribution is the framework and its evaluation protocol, not a claim that SSAI outperforms denser alternatives.
We instantiate SSAI with $K=4$ axes (sentiment, risk, confidence, volatility forecast) on a US-equity panel (30 NASDAQ-100 names, FNSPID news, 2019--2023 test), and evaluate it across direct factor portfolios, supervised ridge forecasters, and RL agents (DP-PPO, SAC) that share the same fixed $\phi$. The four-factor factor portfolio reaches 307.2% cumulative return and Sharpe 1.067, but apparent gains versus buy-and-hold (243.6%) fail coverage-stratified controls, reverse at $\geq 0.2$% costs, and are statistically fragile versus a sentiment-only baseline; a PC1 composite and a FinBERT portfolio baseline are stronger ranking signals in this setting. Ridge and RL blocks diagnose representation versus optimiser effects. We position SSAI as an interpretability-performance diagnostic and reusable protocol for sparse-text decision systems.
| Comments: | 18 pages, 3 figures. NeurIPS 2024 manuscript style (preprint) |
| Subjects: | Machine Learning (cs.LG) |
| ACM classes: | I.2.6; I.2.m |
| Cite as: | arXiv:2605.06730 [cs.LG] |
| (or arXiv:2605.06730v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06730 arXiv-issued DOI via DataCite |
From: Likhita Yerra [view email]
[v1]
Thu, 7 May 2026 11:37:40 UTC (606 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。