Skip to content
View Geoffrey313's full-sized avatar
💭
Working Hard
💭
Working Hard
  • Dimtech
  • Beijijng
  • 01:36 (UTC -12:00)

Block or report Geoffrey313

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.

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
Geoffrey313/README.md

Geoffrey Ducournau — Quantitative Research & AI Architecture

ORCID LinkedIn Email Website

About

Quantitative researcher and AI architect. I hold a PhD in statistical finance and a postdoc in finance from Tsinghua University (School of Economics and Management). My research sits at the intersection of complex systems and financial markets — market microstructure and optimal execution, empirical asset pricing, macro-finance, portfolio allocation, and structural / causal work across markets. In parallel I pursue applied machine-learning research: computer vision, graph neural networks, and anomaly / fraud detection.

On the engineering side I work end-to-end as a Lead R&D & AI Architect: AI research, algorithmic modelling, system and infrastructure design, automation, and production deployment across cloud and on-premise — including the full MLOps lifecycle. I have delivered systems for hedge funds, investment banks, insurance companies and fintech firms.

  • 🔬 Research across complex systems, market microstructure, empirical asset pricing and macro-finance.
  • 🧠 Applied ML: computer vision, graph neural networks, anomaly & fraud detection.
  • 🛠️ End-to-end delivery: modelling → system design → automation → production (cloud & on-prem), with MLOps.
  • 🌏 Based between Paris and Tianjin.
  • 🤝 Open to research collaboration on microstructure and empirical asset pricing — and on complex-systems and macro-financial approaches to asset allocation and portfolio optimisation.
  • ✉️ Reach me via LinkedIn or email.

Explore

Research Engineering

Papers Projects

Toolbox

tech stack

Research & modelling Python PyTorch TensorFlow NumPy pandas Optuna LaTeX

Services & data FastAPI PostgreSQL Redis Kafka MLflow Airflow

Infrastructure & security Docker AWS Azure GitLab CI Grafana Tailscale Linux

Selected work

Current working papers (2026):

Bonds or Gold: The Price of Monetary Trust Safe-haven demand and the price of monetary trust. working paper · 2026

One Growth May Hide Another Financing source, asset growth and stock returns across twenty-four markets. working paper · 2026

The Policy Supply of Low Volatility Volatility suppression and release in foreign-exchange and sovereign-bond markets. working paper · 2026

No News before the News Information flow and price behaviour ahead of announcements. working paper · 2026

From Microprice to Microdiffusion Heavy-tailed price diffusion in limit-order books. working paper · 2026

The fragility ratio Λ When order-book imbalance fails as a signal. working paper · 2026

Migrating Blind How China's Gaokao reform stopped family arbitrage. working paper · 2026

Below the Line Detecting accounting anomalies in Shariah-compliant equities. working paper · 2026

Activity

profile summary

activity graph

contribution snake

Pinned Loading

  1. microdiffusion microdiffusion Public

    Python 1

  2. fragility-ratio fragility-ratio Public

    Python

  3. no-news-before-the-news no-news-before-the-news Public

    Python

  4. price-of-monetary-trust price-of-monetary-trust Public

    Python

  5. self-funded-growth self-funded-growth Public

    Python

  6. shariah-sentinel shariah-sentinel Public

    Python