Reshaping Risk with Investment Technology to Capture Alpha

[The current market demand for enhanced alpha-generating strategies, investment transparency, and operating efficiency in today’s uncertain and volatile markets presents an opportunity for investment technology leaders to bring more solutions to the industry. This also positions forward-thinking investment managers to play a leading role in sparking the next wave of transformation in the asset management industry, including end to end automation of the investment process with the objective of delivering persistent alpha and reducing risk.  

Reston VA based Valspresso - a financial technology and investment strategy development firm – has this mission at its core which motivated them to create and launch a suite of AI-driven, cloud-based applications that automate the entire investment process—from analysis to portfolio construction to trade execution—without human intervention. Their AI-driven sentiment and fundamental indicators analyze all publicly traded companies on the U.S. major exchanges with deep fundamental, as well as a patented price sentiment analysis.  These indicators exhibit strong predictive power and help to manage the risk of investing by identifying those companies that are stable investments. Alpha is delivered through a combination of stock selection, dynamic tactical allocation, and automation.

The Institute decided to explore further by speaking with Valspresso’s management. The firm is led by Founder and CEO, Reginald Nosegbe, the originator of the proprietary methodology described in this interview, along with Ty Seddon, a data science expert with 25 years artificial intelligence and algorithm development experience and Bob Caspe, with 50 years of experience in technology and entrepreneurship. Their most recent step has been to create VALDX - a data feed of their indicators that is licensed and distributed by FactSet - bringing to the market the core elements of their patented investment technology.]

Hortz: Can you share with us the motivations and thought process you originally went through in creating your investment approach?

Nosegbe: As an undergraduate student at the University of Virginia in 1996, I studied the great crashes of the 20th century. I was concerned not so much because of the crashes in and of themselves; but, rather, because of the devastating financial and emotional impact they had on the lives of ordinary people. Then, I read the Federal Reserve Chairman Alan Greenspan’s statement, buried in the middle of a speech, that the market was driven by “irrational exuberance.” What he meant was that crashes had been the result of stock bubbles.

So, I started to ask myself then, if there is something called irrational exuberance how does one objectively quantify it?  To answer this question, I designed an independent study course, outside of the normal curriculum at UVA, to create a mathematical model that would objectively quantify exuberance.  I went on to get a master’s degree in systems and information engineering, giving me the technical rigor to support my mathematical model.  I got a patent for it— a method for precisely measuring market sentiment.

Making a contribution to solving this seemingly intractable problem has been my life’s work. It is this experience: a quest to empower investors to reduce their risk of investing in the stock market, coupled with a dedicated team at Valspresso that shared my passion, that gave me the motivation to bring to market our innovation. In essence, a data-driven, easy to understand, transparent investment approach—undergirded by patented sentiment, proprietary fundamental indicators, and AI-driven systems—that empowers asset owners and asset managers to predictably reduce their risk of investing in the stock market while generating higher Alpha

Caspe: Let me also point out that often it is the coincidence of events that leads to great opportunities.  About the time that Reggie was studying the question of irrational exuberance, the market reporting environment changed radically.  For example, under SEC Regulation FD, it would no longer be possible for companies to share critical information with a select group of analysts or brokers, now everything was open.  Visibility to cash flow data and the balance sheet provided insights to trained CPAs with the ability to really measure a company’s true earnings and structure.  While it may seem simple, the actual analysis to do this is based upon years of study and understanding.  But we believed that we could apply that analysis in an automated way that leads to classifiers that have powerful and consistent predictive power – both for good and also poor performance.

Hortz: Why did you take the road you took in merging two seemingly different approaches into your patented “quantamental” investment methodology?

Nosegbe: The primary goal of active strategies is to outperform a relevant passive benchmark, meaning deliver better risk-adjusted return and alpha. We believe and have demonstrated that in-depth fundamental analysis of companies can be a core input to strategies that deliver superior alpha. We have developed proprietary technologies that automate the entire investment process—from analysis, to portfolio construction, to trade execution—with a clear objective: deliver better returns at lower risk. Our melding of fundamental analysis, quantitative methods, and technology is complementary, enabling the disciplined execution of our alpha-generating investment strategies without human biases.

Hortz: How did you go about developing your sentiment & fundamental Indicators?

Nosegbe: The development of our sentiment and fundamental indicators were driven by clear objectives: 1) the indicators and signals must deliver better return while reducing risk, 2) the achievement of better outcome must be statistically and investment significant, 3) the alpha value of the indicators must persist across market caps, across investment styles, across sectors, across time, and 4) the indicators must have the flexibility to be used by asset managers as alpha-generating input to their unique portfolio management strategies.

Hortz: What kind and level of predictive capability do your indicators exhibit?

Nosegbe: To demonstrate the predictive value of our indicators, we begin by asking the question: selected from a universe, for example the S&P 500, what is the probability of companies in your portfolio outperforming their peers over the next 20 days? For our Fundamental Grade “A” classifier, the probability of outperforming over 20 days is 51% to 53%.  We then ask the question, what is the probability of outperforming in the long run? In the long-run, rolling 3-years, the probability of Fundamental Grade “A” companies (as a class) outperforming the benchmark is 99%, delivering 2.5% alpha on the average and beta less than 1.

It is important to note that the analysis of financial statement data, like 10Ks, 10Qs and 8Ks, is the sole input to the algorithmic model that yielded our Fundamental Grade “A’ outperformance. The model had no knowledge of stock price, analysts’ opinion, or other external data. This is our baseline. Performance can be further improved when other user-defined variables with predictive power (e.g., Valspresso’s sentiment data or dynamic sector allocations) are added to the baseline model.

Hortz: How did you design your artificial intelligence system to automate the entire investment process - from analysis to portfolio construction to trade execution? Why automate the entire process?

Seddon: We chose to automate the entire process in order to align investment objectives, remove human bias, and respond more quickly to changing conditions.  By automating the entire process, we feel like we have developed a more holistic and cohesive understanding that allows us to uncover new insights. 

We apply different AI techniques to different classes of problems within the entire value chain of the investment process.  They roughly fall into 3 categories: Interpretation, Prediction, and Design Optimization.

Fundamental analysis is primarily an Interpretation task.  We believe that transparency is important, so we don’t use any black box machine learning algorithms for this Interpretation phase.  We need to be able to explain why a company is rated as it is.  To do this, we use an expert system to perform deep fundamental analysis on every company, every day. 

For prediction, we aggregate those individual company ratings up to the market and sector levels and have found that they are consistently our most important machine learning features for understanding and responding to current market conditions.

In regards to design optimization, we created a Strategy Designer that is a hybrid of expert rules and machine learning. With the strategy designer any investment manager can develop trading strategies, in a point and click fashion, with the AI guiding users through the process.

Hortz: What role does that leave for the asset manager? How does Valspresso’s indicators empower subscribers to “design and deploy their own persistent alpha-generating strategies”?

Nosegbe: Our goal is not to replace asset managers, but to provide them alpha-generating indicators and signals that can serve as input to their strategies. For example, value, growth, large cap, small cap, or ESG managers can significantly improve the outcome of their strategies by incorporating our fundamental and sentiment indicators into their portfolio design and execution.

Hortz: What feedback and applications are you hearing from advisors and other money managers on your investment technology?

Caspe: To be honest, many say “I already have that data in my feed, I believe that my models should find the same correlations that you found.  Prove to me that I don’t.”  The proof is in the testing, but the rub is that these same quants and analysts have lost confidence in back-testing.  The key for them to appreciate is that our methodology is not a fit to historical data, but rather an invariant process as defined by the accounting industry in how one analyzes a company’s health and stability.  Most quants are trained in mathematics, not accounting.

Hortz: As a systems engineer, inventor, student of economic history, and passionate advocate for investors trying to build and protect their investments, are there any other thoughts or recommendations you would like to share?

Nosegbe: The investment approach that we discussed in this interview provides asset owners (individuals and institutions) tools designed to empower them to significantly reduce their risk of investing in the stock market while improving returns.

We invite advisors and investment managers to visit our website to learn more about our indicators, explore some of our technical research white papers, and see how to apply our investment technology to your investment process, helping you reshape risk to capture alpha.

Related: A Different Approach to Equity Risk Management