Financial markets are among the most challenging and rewarding application areas for data mining and pattern discovery. There is enormous competition to extract faint but meaningful patterns from extremely volatile and noisy signals. 

In theory, timing the market is impossible—and in practice, that is a good first approximation. But, with advanced analytics, new data sources, feature transformations, and customized quality metrics, we have often been able to extract useful predictive signals from the noise, and reliably estimate a quantitative strategy’s quality.

Elder Research’s founding clients in 1995 were hedge funds, and we have had two decades of success in this challenging field. We are able to help clients evaluate, optimize, or create quantitative investment strategies with a measureable edge over the market. Our Data Science consulting expertise has also allowed us to help several government agencies fight fraud in the markets, including leading a project for the Securities and Exchange Commission (SEC) to more accurately price Credit Default Swaps.

Evaluate Investment Strategies

Because of the power of modern analytic techniques, it is often possible to find apparent predictive correlations in the market due to over-fit—where the complexity of a model overwhelms the data or, even more dangerouslyfrom over-search—where so many possible relationships are examined that one is found to work by chance. Wrestling with this serious problem, Dr. John Elder developed a powerful resampling method, called Target Shuffling to measure the probability that a finding could have occurred by chance. It is far more accurate than t-tests and other formulaic statistical methods that don’t take into account the vast search performed by modern inductive modeling algorithms. With this tool, Elder Research can much more accurately measure the “edge” (or lack thereof) of a proposed investment strategy.

Further, to more accurately measure the quality of market timing, or style-switching strategies, Dr. Elder created the DAPY (days ahead per year) criterion. DAPY measures, in days of average-sized returns, the expected excess return for a timing strategy compared to a fair benchmark, which is exposed to the market the same percentage.The Sharpe ratio of a strategy can be thought of as measuring the quality of its returns; the DAPY measures the quality of its timing edge. Together, they are much more useful than Sharpe alone. Most importantly, internal studies have shown DAPY to be better than Sharpe at predicting future performance.

Optimize Investment Strategies

Most investment strategies that we review are found to have serious problems. Though not a welcome result by many of the parties involved, it nevertheless saves everyone much sweat and treasure to discover fatal flaws as early as possible and go another route. A few investment strategies we grade as excellent, and our independent review helps clients invest with confidence before others discover and oversubscribe the talented emerging manager. Some strategies appear promising, but could be even stronger with our assistance. In these intermediate cases, our skills in, and unique tools for, investment modeling and optimization can be engaged. 

For example, John Elder’s PhD dissertation was to create a global optimization algorithm to solve problems in commercial and investment realms. The tool—GROPE (Global Rd Optimization when Probes are Expensive) finds the global optimum value (within bounds) for the parameters of a strategy, using as few probes (experiments) as possible. By that criterion, it was for many years (and may still be) the world champion optimization algorithm.

Create Investment Strategies

In some cases, Elder Research creates complete investment strategies. Our very first investment strategy, in conjunction with the WestWind Foundation, performed extremely well for over a decade. For nine years it was open to outside money, and it outperformed the S&P-500 index each of those years, while having about two thirds of its risk (volatility). A chart of the performance is shown in Figure 1.

Performance of Elder Research Hedge Fund vs. two Indices

Figure 1:  Performance of Hedge Fund vs. two Indices (log scale)

In its first years (prior to those shown in Figure 1 after it was open to outside investors) it achieved very strong returns, but with a lot of volatility, and the client was hesitant to invest serious resources. With use of Target Shuffling we were able to show that the edge was very strong and the project proceeded with confidence. Likewise, at the end, our technology revealed the edge to be fading, so the fund was scaled back and then shortly later shut down. Every investor came out ahead, which is not the usual ending to hedge funds!

Elder Research is currently working on a bond market timing strategy, which has been traded live for two years. It goes long or short weekly in the 10-year bonds of three western countries and is showing promise. It has reasonable returns, vast capacity, and very low correlation to other investment strategies, making it a candidate for use in a large portfolio.

Evaluate Risk and Fraud

Elder Research’s greatest area of activity and experience is in prevention of fraud, waste, and abuse, for commercial firms as well as government agencies. This fraud detection expertise intersected with our investment modeling knowledge as we led a project to improve price estimation for the Securities and Exchange Commission for credit default swaps (CDS). The client was the Office of Quantitative Research (OQR) within the Division of Economic and Risk Analysis (DERA). We created a sophisticated modular calculator for converted par spreads from detailed information about interest rates and transactions.  This enhanced the SEC’s ability to compare CDS prices across time and entities and to better understand the relationship (and possible collusion between) market entities.

There are no guarantees in the world of investing, but at Elder Research, we have found that the practical application of advanced analytics can help investment organizations make the most informed and prepared choices possible. Our investment modeling consulting services can help you and your organization evaluate, optimize, and create investment strategies that deliver the highest return.

 

Request a Consultation