Voodoo Spectrum of Machine Learning and Data Sets
525 Views
I used to be very gung-ho about machine learning approaches to trading but I’m less so now. You have to understand that that there is a spectrum of alpha sources, from very specific structured arbitrage opportunities -> to stat arb -> to just voodoo nonsense.
As history goes on, hedge funds and other large players are absorbing the alpha from left to right. Having squeezed the pure arbs (ADR vs underlying, ETF vs components, mergers, currency triangles, etc) they then became hungry again and moved to stat arb (momentum, correlated pairs, regression analysis, news sentiment, etc). But now even the big stat arb strategies are running dry so people go further, chasing mirages (nonlinear regression, causality inference in large data sets, etc).
In modeling the market, it’s best to start with as much structure as possible before moving on to more amorphous statistical strategies. If you have to use statistical machine learning, encode as much trading domain knowledge as possible with specific distance/neighborhood metrics, linearity, variable importance weightings, hierarchy, low-dimensional factors, etc.
It’s good to have a heuristic feel for the …
I used to be very gung-ho about machine learning approaches to trading but I’m less so now. You have to understand that that there is a spectrum of alpha sources, from very specific structured arbitrage opportunities -> to stat arb -> to just voodoo nonsense.
As history goes on, hedge funds and other large players are absorbing the alpha from left to right. Having squeezed the pure arbs (ADR vs underlying, ETF vs components, mergers, currency triangles, etc) they then became hungry again and moved to stat arb (momentum, correlated pairs, regression analysis, news sentiment, etc). But now even the big stat arb strategies are running dry so people go further, chasing mirages (nonlinear regression, causality inference in large data sets, etc).
In modeling the market, it’s best to start with as much structure as possible before moving on to more amorphous statistical strategies. If you have to use statistical machine learning, encode as much trading domain knowledge as possible with specific distance/neighborhood metrics, linearity, variable importance weightings, hierarchy, low-dimensional factors, etc.
It’s good to have a heuristic feel for the danger/flexibility/noise sensitivity (synonyms) of each statistical learning tool. I roughly have this spectrum in my head:
Very specific, structured, safe
Optimize 1 parameter, require crossvalidation↓Optimize 2 parameters, require crossvalidation↓Optimize parameters with too little data, require regularization↓Extrapolation↓Nonlinear (SVM, tree bagging, etc)↓Higher-order variable dependencies↓Variable selection↓Structure learning
Very general, dangerous in noise, voodoo
This diagram is worth expanding. If anyone has any suggestions, please leave them.
Trending Now
1
Big Data
80 shares3,526 views
80 shares3,526 views
How Big Data Is Helping To Lower Medical Liability Risks
Andrej Kovacevic - October 25, 20182
Artificial Intelligence
97 shares3,763 views
97 shares3,763 views
How Can Augmented Reality Benefit The Manufacturing Industry?
Megan Ray Nichols - October 24, 20183
Machine Learning
33 shares2,847 views
33 shares2,847 views
From Prosper202 To Adroll: Evolution Of Machine Learning In Digital Ads
Ryan Kade - October 24, 20184
Analytics
67 shares3,070 views
67 shares3,070 views
Merging Predictive Analytics Models And WAF For Top-Tier Security
Ryan Kh - October 23, 2018
6
Analytics
77 shares3,528 views
77 shares3,528 views
This Scary Good Marketing Data Proves That Halloween Is A Winner
Kayla Matthews - October 22, 20187
Big Data
47 shares2,779 views
47 shares2,779 views
You must log in to post a comment.