将新闻文本转化为4个可解释的决策坐标，提升投资决策透明度。
Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics
- 用4个命名坐标（情绪、风险、信心、波动率）抽象新闻文本，保持无新闻时中性默认
- 四因子组合收益307.2%，但成本超0.2%后不占优，统计上不如情绪基线
- 适合需要可解释性与诊断能力的稀疏文本决策系统研究者
我们提出语义状态抽象接口（SSAI）：一种将稀疏非结构化文本映射为K个可审计、命名坐标的方法，无新闻日采用中性默认值，旨在分离序列决策系统中的表示假设与优化方差。贡献在于框架与评估协议，而非宣称超越密集方法。我们在美股面板（30只纳斯达克100成分股，使用FNSPID新闻数据，2019–2023测试期）上实例化了K=4个轴（情绪、风险、信心、波动率预测），在直接因子组合、监督岭回归预测器和共享固定ϕ的强化学习代理（DP-PPO、SAC）上进行评估。四因子组合实现累计收益307.2%、夏普比1.067，但相对于买入持有策略（243.6%）的明显优势在覆盖分层控制下失效，成本≥0.2%时逆转，且统计上对情绪基线不显著；主成分1（PC1）复合与FinBERT组合基线表现更强。岭回归与强化学习模块用于诊断表示与优化器的影响。我们将SSAI定位为可解释性-性能诊断工具及稀疏文本决策系统的可复用协议。
原文摘要 · Abstract (English)
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 $ϕ$. 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。