Maximum drawdown constraints in portfolio optimization
Incorporating max drawdown constraints into portfolio optimization is tricky because drawdown is path-dependent.
Approaches I've tried:
Method 3 seems most practical for daily rebalancing competitions.
27 Replies
I'd recommend reading "Quantitative Portfolio Management" by Michael Isichenko. It's the best practical guide I've found.
For those new to the platform: start with the tutorial competition. It has a smaller dataset and more forgiving scoring.
Have you considered using PCA to reduce the dimensionality of the feature space? I found that the first 10 components capture 80%+ of the variance.
I've found that sector neutrality is a key factor in the scoring. Strategies that are long one sector and short another tend to underperform.
Can confirm this approach works. I implemented something similar and jumped from rank 150 to rank 23 in two weeks.
I ran a quick backtest on this idea and got a Sharpe of about 1.2 before costs. Not bad for a simple strategy.
This is a common pitfall. Make sure your features are computed before the prediction date, not on it. That's subtle look-ahead bias.