Ep. 312: Deepak Gurnani on Five Steps for Using AI in Investing

Deepak Gurnani is the Founder and Managing Partner of Versor Investments. He is the former CIO of Investcorp’s Hedge Fund Group and was one of its founding members in 1996. Deepak was also a member of its Management Committee. He retired from Investcorp in March 2013. Prior to Investcorp, Deepak spent six years with Citicorp. In this podcast we discuss: 

• Everyone talks about data being important but gets it wrong.  
• Five steps of applying AI/machine learning in investment management. 
• Conventional vs. alternative and unstructured data. 
• Working with the new frontier of unstructured data. 
• Biggest sin of backtesting – look-ahead bias. 
• Importance of feature engineering, model selection, and the ensemble approach. 
• Addressing AI’s ‘Black Box’ problem. 
• Equity index futures trading strategy. 
• Mid-frequency statistical arbitrage trading strategy. 
• Asset allocation philosophy. 
• Using AI for operations. 
• Innovation is fueled by cross-pollination of ideas across different strategies and research areas. 
• Books mentioned: Stabilizing an Unstable Economy (Minsky), Principles for Dealing with the Changing World Order (Dalio). 

You can follow Deepak’s work here and here. 

(The commentary contained in the above article does not constitute an offer or a solicitation, or a recommendation to implement or liquidate an investment or to carry out any other transaction. It should not be used as a basis for any investment decision or other decision. Any investment decision should be based on appropriate professional advice specific to your needs. You are not permitted to publish, transmit, or otherwise reproduce this information, in whole or in part, in any format to any third party without the express written consent of Macro Hive. This includes providing or reproducing this information, in whole or in part, as a prompt.)