Skip to content
View FranQuant's full-sized avatar
18 followers · 6 following

Block or report FranQuant

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
franquant/README.md

Selected work

Project What it shows Stack
llm‑regime‑allocator LLMs call macro regimes from point-in-time data to set ETF weights. Sharpe 0.83 vs 0.66 for 60/40 (not significant), audited for look-ahead memory. Anthropic OpenAI scikit-learn FRED/ALFRED
multi‑asset‑portfolio‑lab Seven allocation models (MV, Black–Litterman, ERC, HRP…) with shrinkage and vol targeting on 13 ETFs. None beats equal weight on Sharpe after multiple-testing correction. NumPy SciPy pandas pytest
ai‑pairs‑trading OU-based pair selection on LatAm ADRs lifts Sharpe from ≈0 to 0.81; an earnings gate takes it to ~1.05. The news-sentiment overlay fails, and the repo shows why. pandas NumPy EODHD
filings‑qa‑rag‑demo Cited RAG over SEC filings: every claim traceable to a retrieved chunk, citations validated, OpenAI or Anthropic generation. SEC EDGAR OpenAI Anthropic
next‑gen‑agentic‑finance Agentic research patterns in ten steps, ending in an evidence → interpretation → open-gaps handoff for human review. Read-only tools, no execution. Agno Tavily DuckDB MCP
the‑ai‑engineer Four capstones: gradient descent and backprop from scratch, a transformer measuring FOMC textual surprise, and an auditable MCP agent. PyTorch MCP

Pinned Loading

  1. llm-regime-allocator llm-regime-allocator Public

    Agentic AI for systematic asset management: LLMs call market regimes for asset allocation, with forecasting, portfolio construction and evaluation audited for look-ahead memory

    Python

  2. multi-asset-portfolio-lab multi-asset-portfolio-lab Public

    Seven portfolio construction methods (MV, Black–Litterman, MDP, ERC, HRP) with shrinkage and vol targeting, tested walk-forward against equal weight on 13 cross-asset ETFs.

    Python

  3. ai-pairs-trading ai-pairs-trading Public

    OU-selected pairs trading on LatAm ADRs with an earnings gate: Sharpe ≈0 → ~1.05 across an 11-year ablation. Proof of concept.

    Jupyter Notebook

  4. filings-qa-rag-demo filings-qa-rag-demo Public

    Cited RAG over SEC filings: EDGAR ingestion, claim-level citations, switchable OpenAI/Anthropic generation. Runs in Colab.

    Python

  5. next-gen-agentic-finance next-gen-agentic-finance Public

    Agentic finance examples for tool-enabled research workflows, market and macro retrieval, multi-agent analysis, and MCP-native research orchestration.

    Python

  6. the-ai-engineer the-ai-engineer Public

    Four AI engineering capstones: optimization and backprop from scratch, a transformer measuring FOMC textual surprise, and an auditable MCP agent.

    Jupyter Notebook 1