[Machine Learning for Trading] {ud501} Lesson 19: 02-09 The Fundamental Law of active portfolio management | Lesson 20: 02-10 Portfolio optimization and the efficient frontier

this lesson => Buffet said two things

=> (1) investor skill

=> (2) breadth / the number of investments

Grinold's Fundamental Law

breadth => more opportunities to applying that skill => eg. how many stocks you invest in

 IC => information coefficient 

BR => breadth / how many trading opportunities we have

 The Coin Flipping Casino

 

Which bet is better? 

 

Coin-Flip Casino: Risk

Coin-Flip Casino: Reward/Risk 

 

 Coin-Flip Casino: Observations

 

 Coin-Flip Casino: Lessons

(1) higher alpha generates a higher sharpe ratio 

 (2) more execution opportunities provides a higher sharpe ratio 

 (3) sharpe ratio grows as the square root of breadth 

Back to the real world 

 

 IR, IC and breadth

 

 The Fundamental Law

 

skill is harder to be increased than breadth

Skill => introverted

Breadth => extroverted 

Simons vs. Buffet 






 

 What is risk?

 Visualizing return vs risk

 

Building a portfolio 

Can we do better? 

 

Harry discovered the relationship between stocks in terms of covariance 

resulting of the portfolio is not just a blend of the various risks

 right stocks picking => outliers

 Why covariance matters

Mean Variance Optimization 

The efficient frontier 

 

原文地址:https://www.cnblogs.com/ecoflex/p/10977417.html