用自然语言实现个性化税优投资组合推荐，让散户也能享机构级服务。
An Emerging Retail Portfolio Management Application: Personalized, Tax-Aware Reinforcement Learning with Natural Language Goals
- 通过三阶段强化学习系统，将用户自然语言目标转化为投资策略。
- 在14天滚动回测中表现稳定，支持多用户认证与实时券商对接。
- 适合关注税务优化、想用口语描述投资目标的个人投资者。
散户难以获得机构级的个性化税优投资组合管理——现有智能投顾采用静态规则分配，而专业系统又要求高门槛和复杂技术栈。本文构建了一个完整集成测试的应用：基于FastAPI的后端与网页仪表盘，允许用户以自然语言描述目标（如“希望稳健增长，但下月需卖出部分股票付首付”），系统将目标路由至六个投资策略之一，并通过三阶段强化学习生成实时、券商直连的投资建议。该系统包含自监督跨资产编码器、带意图路由的专家混合（MoE）分配策略，以及轻量级LoRA适配器，可基于用户真实交易行为个性化推荐，无需重训练共享模型。系统已完成端到端集成测试，对接活券商API（Alpaca，模拟交易模式），支持多用户认证、预览确认流程、每日邮件摘要及可审计的操作链。虽尚未对真实用户开放，但已通过14天滚动回测（含自助置信区间）进行初步验证。论文还总结了多项工程经验：隐式失效的集成路径、阻塞的第三方接口、端到端实证验证优于依赖检查点元数据，这些对基于外部实时数据的强化学习应用具有普遍参考价值。
原文摘要 · Abstract (English)
Retail investors lack access to the kind of personalized, tax-aware portfolio management that institutional clients take for granted -- existing robo-advisors use static, rule-based allocation, and institutional-grade systems require account minimums and technology stacks unavailable to individual investors. We present a fully built, integration-tested application that closes this gap: a FastAPI backend and web dashboard that let a user describe an investment goal in plain language (e.g. "I want steady growth but need to sell some shares next month for a down payment"), routes that goal to one of six investment mandates, and produces a live, broker-integrated portfolio recommendation from athree-phase reinforcement learning system -- a self-supervised cross-asset encoder, a Mixture-of-Experts (MoE) allocation policy with a learned intent router, and a lightweight LoRA adapter that personalizes recommendations from an individual's revealed brokerage behavior without retraining the shared model. The system is functionally complete and integration-tested end-to-end against a live brokerage API (Alpaca, paper-trading mode), including multi-user authentication, a trust first preview-before-apply confirmation flow, daily email digests, and an auditable action-integrity chain, but has not yet been opened to real end-users; we report this honestly as an emerging, pre-deployment application with a concrete path to full deployment, alongside 14-day walk-forward backtests (bootstrapped confidence intervals included) as preliminary, pre-deployment validation rather than production performance. We also report several practical engineering lessons -- silently-inactive integration paths, hanging third-party API calls, and the value of end-to-end empirical verification over trusting checkpoint metadata -- that we believe generalize to other applied RL systems built on external, live data sources.
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。