Is it legit to compare algo and ANN pair-trading strategies by backtesting them on simulated correlated asset prices?

The idea is to simulate many correlated paths, compute their spreads, and use lagged data on the spreads and ADF test statistics as features for ANN. This is benchmarked against a simple pairs trading strategy where I buy/short the spread when it is +/- 2 standard dev away from its historical mean. What I'm interested is whether these two approaches (traditional algo vs machine learning) are directly comparable?

Submitted August 08, 2017 at 06:41AM by turquoise_gamer


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s