Quantitative risk methodologies for portfolio management

Monday, October 31, 2011

Led by Attilio Meucci, Chief Risk Officer, KEPOS CAPITAL

The seminar provides a self-contained overview of advanced techniques necessary for a quantitative approach to risk management. The class is fast paced: the audience is assumed to be familiar with multivariate calculus, linear algebra, and statistics

08:30 Registration and coffee

09:00 The "Prayer": the ten-step checklist of advanced risk and portfolio management

P0- "P" vs "Q": the two worlds of quantitative finance
P1- Quest for invariance
P2- Estimation / factor models for estimation
P3- Projection to investment horizon
P4- Pricing
P5- Portfolio aggregation
P6- Risk attribution/hedging
P7- P&L evaluation
P8- Optimization
P9- Execution
P10- Ex-post analysis

09:50 Linear Factor Models: technical review, myths, pitfalls and new frontier

From "systematic + idiosyncratic" to "dominant + residual" models
Generalized time-series, cross-sectional and statistical models
Deceptive relationships between factor models and CAPM /APT
"Factors on Demand": on-the-fly, portfolio-specific factor models for hedging

10:30 Morning break

11:00 Estimation risk and generalized stress-testing

Historical scenarios with "Fully Flexible Probabilities"
             - Time weighting
             - Crisp/Kernel state weighting
             - Entropy Pooling weighting with partial information
Conditional Stress-testing: "Fully Flexible Bayesian Networks"
Distributional stress-testing
             - "Copula-Marginal Algorithm"
             - Non-normal copulas for the buy-side with Fully Flexible Probabilities
             - Panic copulas

12:30 Lunch

13:30 Diversification: technical review and new developments

Weight-based diversification measures
Risk-based diversification measures
Diversification measures based on Linear Factor Models
Diversification distribution
"Effective Number of Bets" in arbitrary markets and portfolios

15:00 Afternoon break

15:30 Liquidity risk

Prices, market impact, liquidation policy
Single-security liquidity adjustment
Portfolio-level liquidity adjustment
Conditional convolution and state-dependent, distributional liquidity adjustment
Liquidity-adjusted portfolio statistics

17:00 End of the seminar

About the tutor:

Attilio Meucci is a pioneer in advanced risk and portfolio management. His innovations include Entropy Pooling, Factors on Demand, Effective Number of Bets, Fully Flexible Probabilities, and Copula-Marginal Algorithm. Attilio is the founder of SYMMYS, under whose umbrella he designed and teaches the ARPM Bootcamp and manages the charity One More Reason. Attilio Meucci serves as the chief risk officer at Kepos Capital LP. Concurrently, he is adjunct professor at the Master's in Financial Engineering - Baruch College - CUNY. Previously, Attilio was the head of research at ALPHA, Bloomberg LP's portfolio analytics and risk platform; a researcher at POINT, Lehman Brothers' portfolio analytics and risk platform; a trader at the hedge fund Relative Value International; and a consultant at Bain & Co, a strategic consulting firm. Concurrently, he taught at Columbia, NYU-Courant, and Bocconi University. Attilio is the author of Risk and Asset Allocation - Springer and numerous other publications in practitioner and academic journals. He holds a BA summa cum laude in Physics from the University of Milan, an MA in Economics from Bocconi University, a PhD in Mathematics from the University of Milan and is a CFA chartholder. Attilio is fluent in six languages.