Investing Expertise

What is the best way to conduct quantitative investment research? In his September 2021 presentation package entitled “Escaping The Sisyphean Trap: How Quants Can Achieve Their Full Potential”, Marcos Lopez de Prado outlines the optimal way to tackle such research. Based on his experience, he concludes that: Keep Reading

Do motives of financial market researchers justify strong skepticism of their findings? In his brief August 2021 paper entitled “Be Skeptical of Asset Management Research”, Campbell Harvey argues that economic incentives undermine belief in findings of both academic and practitioner financial market researchers. Based on his 35 years as an academic, advisor to asset management companies and editor of a top finance journal, he concludes that: Keep Reading

Is the WisdomTree approach to exchange-traded fund (ETF) cost efficiency and performance potential (Modern Alpha) attractive? To investigate, we compare performance statistics of six WisdomTree ETFs, all currently available, to those of “easy substitute” (widely used and very liquid) benchmark ETFs, as follows:

1. WisdomTree U.S. Total Dividend Fund (DTD), with SPDR S&P 500 ETF Trust (SPY) as a benchmark.
2. WisdomTree U.S. Earnings 500 Fund (EPS), with SPY as a benchmark.
3. WisdomTree Europe Hedged Equity Fund (HEDJ), with Vanguard FTSE Europe Index Fund ETF Shares (VGK) as a benchmark.
4. WisdomTree Yield Enhanced U.S. Aggregate Bond Fund (AGGY), with iShares Core U.S. Aggregate Bond ETF (AGG) as a benchmark.
5. WisdomTree U.S. Multifactor Fund (USMF), with iShares Russell Mid-Cap ETF (IWR) as a benchmark.
6. WisdomTree 90/60 U.S. Balanced Fund (NTSX), with 90%-10% SPY-iShares 7-10 Year Treasury Bond ETF (IEF) as a benchmark.

We focus on average return, standard deviation of returns, compound annual growth rate (CAGR) and maximum drawdown (MaxDD), all based on monthly data. Using monthly dividend-adjusted returns for all specified ETFs since inceptions and for all benchmarks over matched sample periods through July 2021, we find that: Keep Reading

How well do derivatives traders perform, and why? In the July 2021 version of their paper entitled “Derivatives Leverage is a Double-Edged Sword”, Avanidhar Subrahmanyam, Ke Tang, Jingyuan Wang and Xuewei Yang study the performance of Chinese derivatives (futures) traders across 1,086 contracts on 51 underlying assets. They consider gross and net daily trader returns, turnover and degree of leverage implied by contracts held. They further investigate sources of profits/losses for these traders. To identify clearly skilled (unskilled) traders, they identify those in the top (bottom) 5% of Sharpe ratios who trade on at least 24 days during the first year of the sample period and isolate those with statistically extreme performance. They then analyze trading behaviors and results for these extreme performers the next two years. Using data from a major futures broker in China, including transaction histories, end-of-day holdings and account flows (injections and withdrawals) for 10,822 traders (315 institutional) during January 2014 through December 2016, they find that:

Keep Reading

Should practitioners and academics doing research on financial markets be especially careful (compared to researchers in other fields) when employing statistical inference. In the July 2021 version of their paper entitled “Finance is Not Excused: Why Finance Should Not Flout Basic Principles of Statistics”, David Bailey and Marcos Lopez de Prado argue that three aspects of financial research make it particularly prone to false discoveries:

1. Due to intense competition, the probability of finding a truly profitable investment strategy is very low.
2. True findings are often short-lived due to financial market evolution/adaptation.
3. It is impossible to verify statistical findings through controlled experiments.

Based on statistical analysis principles and their experience in performing and reviewing financial markets research, they conclude that: Keep Reading

When a public pension fund reports beating its benchmark, does that signify a job well done? In his July 2021 paper entitled “Cost, Performance, and Benchmark Bias of Public Pension Funds in the United States: An Unflattering Portrait”, Richard Ennis analyzes net returns of statewide pension funds in the U.S. He calculates both (1) net Sharpe ratio and (2) return versus a matched benchmark constructed via regression as the best-fit combination of the Russell 3000 stock index, the MSCI ACWI ex-U.S. stock index and the Bloomberg Barclays US Aggregate bond index. He compares performance relative to this benchmark and estimated costs for each fund. He then assesses performance of the funds versus the benchmarks they themselves construct and report against. Using self-reported data for a sample of 24 such funds self-reported via the Public Plans Data website during July 2010 through June 2020, he finds that: Keep Reading

Can machine learning-generated stock market crash predictions be amenable to human interpretation? In their June 2021 paper entitled “Explainable AI (XAI) Models Applied to Planning in Financial Markets”, Eric Benhamou, Jean-Jacques Ohana, David Saltiel and Beatrice Guez apply a gradient boosting decision tree (GBDT) to 150 technical, fundamental and macroeconomic inputs to generate daily predictions of short-term S&P 500 Index crashes. They define a crash as a 15-day S&P 500 Index return below its historical fifth percentile within the training dataset. The 150 model inputs encompass:

1. Risk aversion metrics such as asset class implied volatilities and credit spreads.
2. Price indicators such as returns, major stock index Sharpe ratios, distance from a long-term moving average and and equity-bond correlations.
3. Financial metrics such as 12-month sales growth and price-to-earnings ratio forecasts.
4. Macroeconomic indicators such Citigroup regional and global economic surprise indexes.
5. Technical indicators such as market breath and index put-call ratio.
6. Interest rates such as 10-year and 2-year U.S. Treasury yields and break-even inflation level.

They first rank and filter the 150 inputs based on GBDT to discard about two thirds of the variables. They then apply the Shapley value solution concept to identify the most important of the remaining variables and thereby support interpretation of methodology outputs. Using daily values of the 150 model inputs and daily S&P 500 Index roll-adjusted futures prices from the beginning of January 2003 through mid-January 2021 (with data up to January 2019 used for training, the next year for validation and the rest for testing), they find that:

Keep Reading

Overall, how do retail option traders perform compared to institutional counterparts, and what accounts for any performance difference? In their June 2021 paper entitled “Who Profits From Trading Options?”, Jianfeng Hu, Antonia Kirilova, Seongkyu Park and Doojin Ryu use account-level transaction data to examine trading styles and profitability by investor category for KOSPI 200 index options and futures. There are no restrictions in Korean derivatives markets on retail investor participation, and retail participation is high. Using anonymized account-level (153,835 domestic retail, 5,904 domestic institutional, 667 foreign institutional and 604 foreign retail) data for all KOSPI 200 index options and futures trades during January 2010 through June 2014, they find that:

Keep Reading

Why have U.S. public pension, endowment and other non-profit funds (institutional investors) consistently underperformed simple, investible passive benchmarks since 2008? How should they remedy that underperformance? In his April 2021 paper entitled “How to Improve Institutional Fund Performance”, Richard Ennis summarizes prior papers quantifying post-2008 institutional investor returns and recommends how institutions can improve this performance. Extending performance estimates from prior analyses through June 2020, he finds that: Keep Reading

A subscriber provided promotional materials for, and requested assessment of, the Artemis Capital Management Dragon portfolio. General allocations for this portfolio are:

• 24% to secular growth such as U.S. and international stocks.
• 21% to “long volatility and convex hedging” such as the Artemis Vega Fund and tail risk hedges (probably options and/or futures).
• 19% to commodity trend following.
• 18% to interest rate-sensitive assets such as U.S. Treasury bonds, Treasury Inflation-Protected Securities (TIPS) and investment grade bonds.
• 18% to inflation protection such as gold and potentially crypto-assets.

Apparently, the fund has not yet launched and all performance data are backtested (hypothetical). Lacking detail to replicate the Dragon portfolio, we look at its hypothetical monthly returns per promotional materials. We use a 60% SPDR S&P 500 Trust (SPY) – 40% iShares 20+ Year Treasury Bond (TLT) portfolio, rebalanced monthly, as a simple hybrid benchmark. For reference, we also compare results for SPY, the Simple Asset Class ETF Value Strategy (SACEVS) Best Value portfolio and the Simple Asset Class ETF Momentum Strategy (SACEMS) equal-weighted (EW) Top 2 portfolio. Using gross monthly total returns for the Dragon portfolio, SPY, TLT, SACEVS Best Value and SACEMS EW Top 2 during January 2012 through April 2021, we find that: Keep Reading