Quanta Reading Club
A biweekly technical reading community exploring AI, quantitative finance, neuroscience, and quantum computing — through structured sessions, reproducible notebooks, and serious discussion.
Reading Tracks
Structured biweekly reading tracks across quantitative finance, applied AI, neuroscience and markets, and emerging deep-tech methods.
Market Regimes, Risk & Applied ML in Finance
This track takes you from the statistical foundations of financial time series all the way to applied machine learning for regime detection, stress testing, and backtesting. Each session pairs one accessible reading with one serious paper, a reproducible Python notebook, and structured discussion. By the end of Season 1, participants will have built a working knowledge of quantitative risk modeling and regime-aware finance — grounded in real code and real papers.
Cadence
Biweekly
Duration
90 min / session
Location
Online (Zoom)
Cohort size
25–30 participants
Prerequisites
- Basic Python proficiency (numpy, pandas)
- Curiosity about financial markets — no finance degree required
- Willingness to read one paper and engage with one notebook every two weeks
Session Format (90 minutes)
Context & Intuition
Facilitator sets the scene — why this topic matters, real-world framing, key visuals
Paper Discussion
Structured discussion of the core reading — key claims, methodology, limitations
Notebook Walkthrough
Live code demo or pre-recorded walkthrough of the session's Python notebook
Open Discussion
Discussion questions, debate, connections to previous sessions
Project Ideas & Next Steps
Mini-project announcement, preview of next session, participant feedback
Each session produces
Season 1 Roadmap · 12 Sessions
Session Schedule
First 4 sessions announced. Full roadmap revealed after Session 4.
Module 1 — Foundations
Statistical properties of financial returns and volatility dynamics.
Returns, log-returns, non-normality, heavy tails, volatility clustering, and leverage effects.
Accessible Reading
Statistics and Data Analysis for Financial Engineering — Chapter 1 — Ruppert & Matteson
Core Paper
Empirical Properties of Asset Returns: Stylized Facts and Statistical Issues — Rama Cont (2001)
Discussion Questions
- 1Why are financial returns difficult to model with standard statistical tools?
- 2Why does the normality assumption fail — and why do practitioners still use it?
- 3Which stylized facts matter most for risk management vs. alpha generation?
Mini-Project Idea
Repeat the stylized facts analysis on a different asset class (crypto, commodities, or FX) and compare. Do the same stylized facts hold?
Module 2 — Market Regimes
Detecting and modeling structural states in financial markets.
Module 3 — Risk, Stress & Antifragility
Tail risk measurement, stress testing, and crisis-aware system design.
Module 4 — Machine Learning for Finance
Applied ML for financial time series, backtesting, and the capstone project.
Register for Reading Club Updates
Register to receive session invitations, reading materials, and notebook releases for the tracks that interest you. No commitment required — you can start with updates and join live sessions when you are ready.
The Reading Club is free to join. Live session participation is limited to 25–30 members per cohort.
Reading List
Core papers, books, and resources referenced across sessions.
Empirical Properties of Asset Returns: Stylized Facts and Statistical Issues
Rama Cont
The foundational survey of stylized facts in financial return distributions — fat tails, volatility clustering, and the leverage effect. Essential reading for anyone working with financial time series.
Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation
Robert F. Engle
The original ARCH paper that launched a family of volatility models still used in risk management and derivatives pricing today. A landmark in financial econometrics.
Regime Changes and Financial Markets
Ang & Timmermann
A comprehensive survey of regime-switching models in finance — covering detection methods, economic interpretation, and applications to asset allocation and risk management.
Detecting Bearish and Bullish Markets in Financial Time Series Using Hierarchical Hidden Markov Models
Nystrup et al.
Applies hierarchical Hidden Markov Models to detect multi-scale market regimes. An accessible and practically focused paper ideal for practitioners building regime detection pipelines.
Advances in Financial Machine Learning
Marcos López de Prado
The definitive guide to applying machine learning rigorously in finance — covering feature engineering, backtesting, overfitting, and the structural differences between financial and standard ML problems.
Session Notes & Technical Outputs
Our Values
The principles that guide how we read, discuss, and build understanding together.
Rigorous Reading
We engage with original papers, technical articles, and serious source material.
Open Discussion
Every serious perspective is welcome. We debate ideas, assumptions, and methods, not people.
Collaboration
Learning is a collective process. We build understanding through discussion and shared curiosity.
Intellectual Curiosity
We follow questions across disciplines — from AI and markets to neuroscience and emerging technologies.