Investing Expertise

Can machine learning perfect equity sector rotation? In the January 2023 version of their paper entitled “Deep Sector Rotation Swing Trading”, flagged by a subscriber, Joel Bock and Akhilesh Maewal present a sector rotation strategy guided by multiple-input, multiple output deep learning model. The strategy chooses weekly from among 11 U.S. sectors using exchange-traded fund (ETF) proxies. Specifically, each week during each year, they:

• Train the machine learning model on the last two years of weekly (Friday close) historical sector ETF prices and volumes and sometimes auxiliary economic data (10-year U.S. Treasury yield, USD currency index, crude oil proxy and stock market volatility) to predict next-week opening and closing prices for each ETF.
• Compare the predicted return estimate for each ETF to a dynamically updated threshold return to screen for potential buys.
• Apply additional filters to screen out potential buys with unusual past losses to accommodate investor loss aversion.
• At the next-week open, allocate available capital to surviving sector ETFs based on respective past win rate (profitable trade) and respective past sector trade momentum.
• Liquidate all positions just prior to the next-week close.

Their benchmark is buying and holding the S&P 500 Index with reinvested dividends. Using weekly inputs as described during January 2012 through December 2022, they find that:

Keep Reading

Does aggregate insider stock buying and selling offer clues about future stock market returns? In their January 2023 paper entitled “Aggregate Insider Trading in the S&P 500 and the Predictability of International Equity Premia”, Andre Guettler, Patrick Hable, Patrick Launhardt and Felix Miebs investigate relationships between net aggregate insider trading and future stock market excess returns at horizons from one month to one year. They define net aggregate insider trading as unscheduled open market insider purchases minus sales, divided by purchases plus sales. They focus on S&P 500 firm insider trading and S&P 500 Index excess returns (relative to the U.S. Treasury bill yield). They also consider U.S. non-S&P 500 insider trading. They further look at insider trading and stock market excess returns within Canada, France, Germany, Great Britain and Italy. Using monthly aggregations of the specified insider trading data from 2iQ and monthly stock market index returns during January 2004 through December 2018, they find that:

Keep Reading

A subscriber suggested an update of “GMO’s Stunningly Accurate Forecast?” with out-of-sample testing of GMO forecasts. To investigate, we test GMO’s 7-Year asset class real return forecasts of December 31, 2010, July 31, 2013, June 30, 2014 and November 2015. We first match the 11 GMO asset classes covered in these forecasts to exchange-traded funds (ETF), as follows:

1. U.S. equities (large cap) – SPDR S&P 500 ETF Trust (SPY).
2. U.S. equities (small cap) – iShares Russell 2000 ETF (IWM).
3. U.S. high quality – Invesco S&P 500 Quality ETF (SPHQ).
4. International equities (large cap) – iShares MSCI EAFE ETF (EFA).
5. International equities (small cap) – iShares MSCI EAFE Small-Cap ETF (SCZ).
6. Emerging equities – iShares MSCI Emerging Markets ETF (EEM).
7. U.S. bonds (government) – iShares 20+ Year Treasury Bond ETF (TLT).
8. International bonds (government) – SPDR Bloomberg Barclays International Treasury Bond ETF (BWX).
9. Emerging bonds – iShares J.P. Morgan USD Emerging Markets Bond ETF (EMB).
10. Inflation-indexed bonds – iShares TIPS Bond ETF (TIP).
11. Short-term U.S. Treasuries (30 days to 2 years) – iShares 1-3 Year Treasury Bond ETF (SHY).

We adjust monthly ETF returns for inflation using monthly changes in U.S. Consumer Price Index (CPI). We then calculate the real compound annual growth rate (CAGR) for each over specified forecast horizons. Using GMO forecasts, dividend-adjusted ETF prices and CPI data during December 2010 through November 2022, we find that: Keep Reading

Should investors presume that, in the absence of falsifiable theories, the body of factor investing research is largely spurious? In the January 2023 version of his paper entitled “Causal Factor Investing: Can Factor Investing Become Scientific?”, Marcos Lopez de Prado reviews the current state of confusion about causality in factor investing research and discusses ways to resolve that confusion. Specifically, he addresses:

• Differences between association and causation.
• Why the study of association alone does not create scientific knowledge.
• How observational studies, natural experiments and simulated interventions support investigation of causality.
• The current state of causal confusion in econometrics and factor investing studies.
• How to transform factor investing into a truly scientific discipline.

Based on many references and the logic of the scientific method, he concludes that:

Keep Reading

Given that finance is ultimately tied to human emotions, does the body of research support belief that abilities of machine learning to handle large amounts of data, non-linearities and variable interactions will revolutionize investing? In their January 2023 paper entitled “How Can Machine Learning Advance Quantitative Asset Management?”, David Blitz, Tobias Hoogteijling, Harald Lohre and Philip Messow study application of machine learning to investing from the perspective of a prudent practitioner. They define machine learning models as initially guided software programs that subsequently learn by themselves and then make predictions about unseen (out-of-sample) data. They describe benefits and pitfalls of machine learning versus classical (linear regression) econometrics. They discuss critical design choices for applying machine learning models to asset management. They focus on the ability of machine learning to beat the stock market, but also discuss asset risk forecasting, optimal portfolio construction and trading optimization. Based on the body of research and their collective experience in asset management, they conclude that: Keep Reading

What is the critical success factor for experienced traders? In their December 2022 paper entitled “Strategic Sophistication and Trading Profits: An Experiment with Professional Traders”, Marco Angrisani, Marco Cipriani and Antonio Guarino compare results from a competitive trading game, a competitive guessing game and individual cognitive/risk preference/personality tests to determine what characteristics most strongly relate to trading success. They recruit two groups for testing: (1) professional traders and portfolio managers working in London financial markets; and, (2) as a control, a gender-matched (mostly male), multi-disciplinary group of undergraduate students with little or no experience trading real markets. For each group, they conduct:

1. A competitive group trading game wherein participants trade an asset that earns dividends over multiple periods in a continuous double auction. Profits derive from both dividends accrued (fundamental value) and any capital gain (ability to outwit other players by buying low and selling high).
2. A competitive group guessing game wherein each participant chooses a number from 0 to 100 with the goal of guessing the number is closest to two thirds of the average choice. Choices reveal how deeply participants reflect on the thinking of others.
3. An individual guessing game (to disentangle reasons for group guessing game outcomes), two tests of cognitive ability (intelligence), tests to elicit risk preferences/confidence and personality traits.

Using game/test results for 56 professional traders and 56 undergraduate students, they find that: Keep Reading

Should investors believe that long-term asset class return forecasts are useful? In his brief August 2022 paper entitled “How Accurate are Capital Market Assumptions, and How Should We Use Them?”, Mike Sebastian employs 10 years of annual Survey of Capital Market Assumptions by Horizon Actuarial Services to assess the industry’s ability to gauge 10-year future asset class returns. This survey presents inputs from leading consulting and investment management firms and includes composite, minimum and maximum forecasted returns for 15 asset classes. Using forecast data for 2012 through 2021, he finds that: Keep Reading

Is past rolling maximum drawdown, a simple measure of recent downside risk, a useful indicator of future mutual fund performance? In their June 2022 paper entitled “Maximum Drawdown as Predictor of Mutual Fund Performance and Flows”, Timothy Riley and Qing Yan investigate whether style-adjusted maximum drawdown based on daily returns over the last 12 months usefully predicts mutual fund performance. To adjust for fund style differences, they subtract from each individual unadjusted drawdown the average unadjusted drawdown across all funds in the same style during the measurement interval. Their principal performance metric is alpha based on a 4-factor (market, size, book-to-market, momentum) model of stock returns. Using daily net returns for 2,188 actively managed long-only U.S. equity mutual funds that are at least two years old and have at least $20 million in assets during January 1999 through December 2019, they find that: Keep Reading

Do presumably expert early-stage startup investors, whether individuals (Angels) or institutions (Venture Capitalists) invest efficiently? In his June 2022 paper entitled “Predictably Bad Investments: Evidence from Venture Capitalists”, Diag Davenport applies machine learning methods based on information known at the time of investment to evaluate decisions of early-stage investors. He defines early-stage investments as equity deals within two years of incubator completion categorized in Pitchbook as deal types Series A, Series B, Seed Round or Angel (Individual). He define late-stage exit as initial public offering, merger/acquisition or funding categorized in Pitchbook as Series C or later. He uses his first five years of quantitative data and numerical transformations of the qualitative data (text) in training a model with XGBoost to predict future venture success. He then applies the model to the next three years of data to build a portfolio that substitutes conventional investments (such as the S&P 500 Index) for predictably bad ventures. Using venture financials and qualitative information about the CEO from Pitchbook for 16,054 startups accepted into top accelerator programs during 2009 through 2016 (2009-2013 for model training and 2014-2016 for testing), he finds that:

Keep Reading

Do individual investors who chase stocks with high recent returns benefit from momentum or suffer from reversal? In their June 2022 paper entitled “Who Chases Returns? Evidence from the Chinese Stock Market”, Weihua Chen, Shushu Liang and Donghui Shi investigate the characteristics, performance and market impact of retail stock investors who exhibit return-chasing behavior. Each month, they measure:

1. Each retail investor’s return chasing propensity (RCP) as the average of returns during the 12 months prior to purchase across the stocks in the investor’s portfolio. For robustness they also consider past return intervals of one, two, three and six months.
2. Each stock’s return chasing ownership (RCO) by wealth-weighting the RCPs of its retail holders (excluding this stock from holder RCP calculations).

Using monthly stock holdings, trading records and investor demographics, plus associated monthly stock prices, for 18 million Shanghai Stock Exchange retail investors during January 2011 through December 2019, they find that:

Keep Reading