Traders are developing quantitative skills in order to apply a systematic and structured approach to trading and execution analysis.
In June’s show, Enrico Cacciatore, senior quantitative execution trader for Voya Investment Management explains how quant traders approach the market, and reveals what investors ought to ask of their asset manager’s quant trading desks.
Dan Barnes: Welcome to Trader TV Equities – your insights into the trading climate for professional equity investors. I’m Dan Barnes. In June’s show we’ll be talking with Enrico Cacciatore, senior quantitative execution trader for Voya Investment Management, about the way quant funds execute trades and the difference this has upon investment strategy and alpha generation. Enrico, welcome to Trader TV.
Enrico Cacciatore: Dan, thank you for having me.
Dan Barnes: Now, when quantitative trading is used, does it change whereabouts in the investment process alpha can be generated?
Enrico Cacciatore: Great question. I think the key thing about alpha generation is that it’s all dependent on the alpha signal duration, so you have very high frequency, trading funds that are looking at durations of milliseconds up to a day, to where you’re looking at mid frequency, where the alpha signal might be hours to several days, or in the case of where we’re looking at months to quarters to potentially a year. So, the critical thing for the trading desk as they trade, is to understand what is the alpha expectation? And obviously, if it’s a very short signal, we have to be cognizant of that and be much more aggressive in how we trade vs if we have a longer signal duration, we’re much more passive in nature and willing to take time to execute to minimize that transactional cost.
Dan Barnes: As quantitative trading has become more predominant, how has that affected the skillset that traders need to have?
Enrico Cacciatore: Quantitative trading is very process, systematic driven. You look at skillsets for quantitative traders, and not only quantitative traders, but for the fundamentally active traders, the need for programing skills, analytical skills, mathematical skills related to optimization. So you’ll hear certain skillsets of Python, KDB, C++ for data analysis, mostly because of the introduction and implementation of advanced, systematic data science that’s being utilized in the trading as well as in the optimization process for the the fund managers.
Dan Barnes: I hear a lot about machine learning and artificial intelligence often attached, slightly in a hype way – to certain technologies being sold, but those are genuinely being used on quantitative trading desks?
Enrico Cacciatore: 100%. One of the things that we’ve been implementing because we utilize a lot of sell-side, algorithmic solutions is, historically the trading desk has picked the broker, not only the strategy and other sub factors, but also the broker itself. And what we’ve done is created what we call algo wheels. Now in an algo wheel, essentially, the trader gets to pick the strategy and the urgency and through machine learning, we will randomly choose brokers. And over time from the data set, it will determine, based on an urgency and strategy, who is performing best and then start to overweight those brokers that perform well. And essentially, you reward those who perform well and you penalize those who underperform, and that’s a basic, machine learning technique of which there is a sub-category of artificial intelligence.
Dan Barnes: How does engagements in the equity market for a quantitative trader differ from engagements in the fixed income market?
Enrico Cacciatore: The big challenge right now for the fixed income space is that it’s evolving very slowly over time to be more transparent, more products-traded, and exchange traded products. The challenge right now for a quant fund trading fixed income products is that transparency, the interconnection of liquidity. And I think the response to that has been the growth in ETF products that express that exposure, that have liquidity that is easily transacted for a quant trader to utilize. So I think the big difference is that liquidity and transparency and being able to trade electronically, and as time goes by and as regulations change within that asset class, I think you will see continued growth in quant managers on the fixed income product side.
Dan Barnes: And does the data that you need for trading each of those asset classes then have different characteristics?
Enrico Cacciatore: As long as we can align the data and have efficient and clean access to historic data, it is really relevant what sort of asset class you’re trading, and that’s the key attribute.
Dan Barnes: And then finally, if investors are looking to invest with a firm that uses quant traders or has quant funds, what sort of questions might they ask to understand the processes?
Enrico Cacciatore: That’s a great question, and I think the key thing is the trading desk being an integral part of the process of alpha generation. The quant funds are using an optimizer, and within that optimizer they should understand the trading cost, trading exposure, and for the trading desks to be part of that. And so the the PM and the trading desk should be one, working in tandem, looking at pre-trade, post-trade cost, evaluating how you can do better, but also having an innovative feedback loop to improve that process over time. And also being able to convey that to the investors of, ‘what you’re doing. How are you doing it? What’s your expectation? How is trading performance?’ And I think those are the key questions to be asking a quant fund.
Dan Barnes: That’s been fascinating. Enrico, thank you very much for coming on the show.
Enrico Cacciatore: Thank you so much, Dan.
Dan Barnes: I’d like to thank Enrico Cacciatore of Voya Investment Management, and of course you for watching. To catch our monthly reports on other markets or to subscribe to our newsletter go to TraderTV.NET.