Hedge fund that exploits human-machine biases annualises +11%

view original post

Andy Chakraborty
B. G., Opalesque Geneva for New Managers:

Combining long/short equity investing with researching and trading human/machine behavioural biases has been a recipe for success for this New York-based fund manager.

Duo Reges Capital Management employs a quantamental behavioural equity long/short strategy designed to have a low correlation to the markets.

“We exploit human-machine behavioural biases in financial markets using a quant-based equity long/short strategy,” portfolio manager Uzi Hadar, CFA, explains to Opalesque. “Human-machine behavioural biases are the side effects of market innovations such as ESG, social investing/apps, and other rule-based investments. These biases cause persistent market inefficiencies. Our algorithms identify the signature of the biases and take long and short positions to exploit them.”

The hedging is done through the systematic use of ETFs, vanilla options, invoked pairs trading, and negatively correlated return drivers.

Portfolio manager Andy Chakraborty will be presenting at the Small Managers – Big Alpha Episode 6 webinar on January 11th, 2022.

Prior to starting Duo Reges, Chakraborty led quantitative and analytics teams at several tech sector firms including Amazon, Microsoft, and Intel.

“I spent more than 20 years – most recently as Chief Data Scientist at Amazon S3 and Retail Systems – on solving problems where even world-class models fail,” Chakraborty says. “There are many inefficiencies in capital markets resulting from both investment decision-making (human biases) and the intersection between those human behaviours and machine-based investing. It was a natural progression to apply the successful strategies I had been employing at top tech firms to the financial markets. I founded Duo Reges in 2018 to exploit the market inefficiencies identified by our proprietary models.”

The fund, Duo Reges ISA, returned 40% from its November 2018 inception to November 2021, annualising 11.6% net – compared to 6.5% for the HFRX Equity long/short index and 5% for the HFRX Global Hedge fund index.

The HFRX Global Hedge Fund index returned 3.7% in 2021, and the HFRX Equity Hedge index 12.2%.

The fund has recently relaunched under Alpha Innovations (AI), a new state-of-the-art asset management platform, with offices in New York, consisting of deeply vetted managers with unique alpha generation capabilities, and $40m under management. An offshore feeder will be launched soon.

“Andy and the Duo Reges team have a very specific methodology for employing alternative data in an uncommon way, allowing them to understand investor biases and use that knowledge to generate uncorrelated returns,” noted Lawrence Newhook, CIO of AI. “They are a perfect example of the type of unique talent and differentiated approach to alpha generation which is the hallmark of AI strategies.”

Human-machine collaboration

Duo Reges, which means “two kings” in Latin, focuses on the “hard edges” of how humans and machines collaborate in the financial markets, both successfully and unsuccessfully. Its core strategy is to forecast the resulting long and short momentum by clustering market participants into “personas” to which it recommends securities they will like (longs) or dislike (shorts).

In a paper published on the CFA Institute’s site, Uzi Hadar and Andy Chakraborty say that algorithmic / machine-learned / artificially intelligent (AI) tools are increasingly ubiquitous in the investing world. These tools will surface in even the most fundamentals-oriented discretionary buy-and-hold investor’s research process. “The right focus then is on “model awareness”,” they explain. “How can we leverage the fact that machine learning, alternative data, and AI are not only widespread but increasing in influence?”

To be model aware, every investor should start with the process question: Where is the most opportunity and risk? Their answer is that it lies with people.

“Remove human drivers and pedestrians from the roads and self-driving cars would perform flawlessly,” they argue. “The collaboration between humans and machines is the ‘lowest bandwidth’ connection each has. Think about how easily we can turn a doorknob and walk outside or a computer can render a complex image. Compare that to how hard it is to represent our problem or obtain feedback about its results. Human-machine collaboration is both the key to success and an opportunity vector to exploit.”

The term quantamental is a combination of quantitative and fundamental and thus refers to an investment strategy that involves combining quantitative and fundamental approaches to investing. This combination, according to International Banker, is often regarded as a melding of man and machine: the investor harnesses the scale and power of data and blends it with the benefits of human insight in order to unearth winning investment strategies.



Small Managers – BIG ALPHA Episode 6

We are proud to present you the next episode of this groundbreaking webinar series with the following carefully screened panel of investment managers:

• Andy Chakraborty, Duo Reges Capital Management
Lukasz Tomicki, LRT Capital Management
Steven Grey, Grey Value Management
Scott Phillips, Lavaca Capital

When: Tuesday, January 11th at 10:30 am ET – 3:30 pm UK time – 4:30 pm CET

Free registration here: www.opalesque.com/webinar/