金融数值预测与分配：以 token 生成的方式实现
Financial Numerical Prediction and Allocation as Token Generation
浏览论文内容
中文总结 AI 辅助
本研究提出 FinATOM 框架，通过因果语言模型的 token 生成实现金融数值预测与 ETF 分配，在多组测试中显著提升了夏普比率与累计收益，验证了该方法的可行性。
中文摘要 AI 辅助
金融预测通常依赖于任务特定的回归、排序或策略头，将语言模型与最终评估的数值对象分离开。我们研究因果语言模型是否可通过受约束的 token 生成直接表示预测与决策。FinATOM 为三步股票收益预测及动态五只 ETF 分配引入了统一的无头部接口。预测模型自回归地输出经波动率标准化的收益 token，训练时先采用序数与排序监督，再进行单 epoch 的 token 级策略阶段。分配模型生成归一化的多头权重；监督微调（SFT）模仿因果均值-方差锚，经 DAPO 增强的 GRPO 在锚一致性约束下优化已实现的 21 天夏普比率。在 2023-2025 年的 ETF 测试中，该分配策略将汇总总夏普比率从 1.428 提升至 1.529，在 5 个基点交易成本模型下的净夏普比率从 1.394 提升至 1.494；多模态分配输入获得最高的三期平均夏普比率 1.540，其优势在 2025 年最为明显。在 FinTexTS 上，SFT 与策略策略分别实现 73.52%/2.68 和 73.72%/2.69 的累计收益/夏普比率。这些结果支持语言模型直接生成 token 用于金融数值预测与决策的可行性，同时推动在不同资产、市场环境及随机种子下开展更广泛测试。
英文摘要
Financial prediction typically relies on task-specific regression, ranking, or policy heads, separating the language model from the numerical object ultimately evaluated. We investigate whether a causal language model can instead represent forecasts and decisions directly through constrained token generation. FinATOM introduces a unified, head-free interface for three-step stock-return forecasting and dynamic five-ETF allocation. The forecasting model autoregressively emits volatility-standardized return tokens and is trained with ordinal and ranking supervision followed by a one-epoch token-level policy stage. The allocation model generates normalized long-only weights; supervised fine-tuning imitates a causal mean--variance anchor, and DAPO-augmented GRPO optimizes realized 21-day Sharpe subject to anchor consistency. In 2023--2025 ETF tests, the allocation policy improves pooled gross Sharpe from 1.428 to 1.529 and net Sharpe under a 5-bp transaction-cost model from 1.394 to 1.494. The multimodal allocation input attains the highest three-period mean Sharpe of 1.540, with its clearest advantage in 2025. On FinTexTS, the SFT and policy strategies achieve 73.52\%/2.68 and 73.72\%/2.69 cumulative-return/Sharpe, respectively. These results support the feasibility of direct language-model token generation for financial numerical prediction and decision-making, while motivating broader tests across assets, regimes, and random seeds.
