The Predictive Alpha blog is about quantitative investing focusing on backtesting trading strategies, statistics, machine learning, data-driven research, programming and practical concepts in trading. The goal is to present interesting problems and show how to overcome those based on our experience with quantitative investing.

Contact us at: predictivealpha@gmail.com



2 thoughts on “About

  1. Studies have shown that factors work better when each one picks stocks rather than when they are all used in one model. Also, 6 to 12 months are usually used for a momentum look back. I’d be curious to see this redone with those changes.


  2. Hi Govind,

    Thanks for your comment.

    Can you please send link to those studies. I would like to read them.

    Yes, 6 and 12 months momentum are normally used, but are they better? The studies you have read did they bootstrap the 6/12 months momentum to get robust statistics not impacted by outliers (something that is an issue in momentum strategies)? Were the studies only on US equities? We will soon launch a series of studies instead momentum/trend-following and here we will go more into details.

    We will run the code again selecting the best from each factor instead of the best from the combined score.


If you have something intelligent to add, please write a comment

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

WordPress.com Logo

You are commenting using your WordPress.com 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