Haha, loved the ML analogy, especially the regularization framing.
I come from a CS/AI background too, and I agree that the real world is not equal to the training set, the idea translates very well into investing.
That said, I’m not fully convinced that quant is “optimization without humility.” Well-designed systems are usually built on the assumption that we’re wrong more often than we think, which is why constraints like position sizing and diversification exist in the first place.
Sometimes removing discretion is exactly what keeps us from overfitting.
Fair pushback, and you got me — "optimization without humility" was too broad. Didn't mean to throw the quant world under the bus.
Good quant systems do have humility built in, often more than discretionary investors.
What I really meant was the LTCM failure mode: model so good you forget the training set isn't the real world. That can happen to value guys too, honestly.
And your last line is sharper than anything I wrote — removing discretion can be exactly what saves you from overfitting. Fair.
Haha, loved the ML analogy, especially the regularization framing.
I come from a CS/AI background too, and I agree that the real world is not equal to the training set, the idea translates very well into investing.
That said, I’m not fully convinced that quant is “optimization without humility.” Well-designed systems are usually built on the assumption that we’re wrong more often than we think, which is why constraints like position sizing and diversification exist in the first place.
Sometimes removing discretion is exactly what keeps us from overfitting.
Fair pushback, and you got me — "optimization without humility" was too broad. Didn't mean to throw the quant world under the bus.
Good quant systems do have humility built in, often more than discretionary investors.
What I really meant was the LTCM failure mode: model so good you forget the training set isn't the real world. That can happen to value guys too, honestly.
And your last line is sharper than anything I wrote — removing discretion can be exactly what saves you from overfitting. Fair.
Thanks for the careful read.