The Case For Quantitative Equities

Improve Diversification and Add Protection to Your Portfolio

Overview

Above average equity market returns since the last recession, coupled with the historic length of the current expansion, have led many investors to consider ways to de-risk their equity exposures in recent years. Naturally, without having perfect knowledge to time the next correction, investors are often hesitant to trade out of equities for fear of missing out on further gains. These concerns are particularly germane as stock markets are currently trading back at all-time highs following bouts of volatility in early and late 2018. One solution to this conundrum is a diversified quantitative equity strategy. A robust quantitative equity portfolio strategy can offer down-side protection in a correction as well as the potential to generate strong positive returns should markets continue to perform. Below, we explain what this emerging style of equity investing is and outline a case for how its unique characteristics can help investors meet their goals irrespective of market environment.

What is Quantitative Investing?​

Quantitative (or “quant”) strategies can be described as systematic and process-driven investment approaches that rely heavily on automation and the integration of ever-growing data sets, computational methods, and processing capabilities. Most quant managers incorporate the same fundamental and technical data points into their investment analysis as discretionary managers, but a quant manager may do so in a systematic and automated manner in which research, security selection, portfolio construction, and risk management parameters are precisely defined up-front. Quant managers may also utilize larger, non-traditional data sets to capture additional investment insights. Through a systematic approach, quant managers will seek to capture trading advantages associated with their breadth of data coverage, agility in processing information, and objectivity in avoiding behavioral biases. They may also retain and integrate institutional knowledge and intellectual property into their investment process.

Buzz words like “artificial intelligence” (AI) and “machine learning” are often referenced when describing quant investing but do little to demystify the strategy. In fact, the mathematical models and theories underpinning AI and machine learning methods are often not new to academics or investment professionals. However, the ability of portfolio managers to apply these methods on a wide array of new data sets has been a major development over the last 5-10 years. Specifically, the availability of “big” and “alternative” data sets, the reduction of barriers-to-entry for computational horsepower and storage (i.e. cheaper hardware and cloud computing), and the innovative ways in which insights have been applied to investment management have all contributed to meaningful advances in quant investing.

What is Big Data and Alternative Data?​

Big data refers to a field of study in which large, complex, and diverse sets of data are analyzed to extract valuable information. Big data is unique in that the variety, velocity, and volume of data is growing at an accelerating rate due to improvements in technology and the increasing connectivity of our world. Alternative data is simply the name given to big data sets that are used to expand insights into the investment process beyond those available from traditional market and financial data sets such as price, volume, earnings metrics, etc. Alternative data can be collected from social networks, websites, personal electronics and apps, questionnaires, product purchases, and electronic check-ins. The presence of sensors and other inputs in smart devices and across commercial/public information systems allows for data to be gathered across a broad spectrum of situations and circumstances.

Impact of Quantitative Investing

The potential insights available to investors by accessing growing alternative data sets are substantial. It is possible that we are in the midst of a leadership change whereby fundamental analysts begin to lose a previously held edge over quantitative methods due the broader application of analytical tools on more comprehensive sets of data.