Image Source: PexelsInvesting formulas are simple, easy-to-implement, systematic, stock screeners that provide instructions on how to outperform the total stock market. Marcel Schwartz and Matthias Hanauer, authors of the December 2024 study, “Formula Investing,” evaluated the effectiveness of four such popular investing formulas over the period 1963-2022:

Their analysis was based on the comprehensive CRSP/Compustat universe, but excluded microcaps to dismiss concerns that tiny stocks, often illiquid and hard to trade, drive the results. Their sample consisted of companies with a minimum market capitalization of $450 million and an average of almost  $31 billion as of December 2022. The average number of stocks was 921, ranging from a low of 298 firms in July 1963 to a high of 1,163 in April 2002.Schwartz and Hanauer sorted stocks into decile portfolios and computed their raw and risk-adjusted performance. Portfolios were updated at the end of each quarter, using the latest price and stock data at formation and yearly accounting data with a reporting lag of at least six months. They also regressed the top-minus-bottom return spreads on common asset pricing factors to determine how much of the formulas’ performance was attributable to their exposure to these factors. Finally, they adopted a “do-it–yourself” (DIY) investor’s perspective by forming concentrated long-only portfolios of the 40 best-ranked stocks for each formula and evaluating their performance in the post-2000 period.Following is a summary of their key findings:All formulas produced near-monotonically increasing returns when sorting stocks into decile portfolios.The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained. Indexes are unmanaged and do not reflect management or trading fees, and one cannot invest directly in an index.

The results are hypothetical results and are NOT an indicator of future results and do NOT represent returns that any investor actually attained.  Indexes are unmanaged and do not reflect management or trading fees, and one cannot invest directly in an index.Their findings led Schwartz and Hanauer to conclude:

“The investigated investment formulas are relatively easy to implement, which distinguishes them from more complex and sophisticated models, such as machine-learning prediction models, which have become popular in recent years. Although these more complex models typically provide higher gross returns, they also entail higher turnover and transaction costs. Moreover, investors may encounter additional investment barriers, including limited access to the necessary data, missing infrastructure to process the data, or the inability to execute the resulting signals in a timely and efficient manner. These more sophisticated models present therefore only genuine opportunities for those investors who are able to overcome these challenges. In contrast, the investigated investing formulas provide investors with efficient exposure to established factor premiums and are relatively easy to implement.”

Investor TakeawaysSchwartz and Hanauer demonstrated that simple, easy-to-implement, systematic formula-based investing can still generate market outperformance, providing investors with efficient exposure to well-documented factor premiums. Note that the concentrated DIY formulas, with just 40 holdings, will have greater exposure to the common factors because of their limited size. They also then take on more idiosyncratic risks that a mutual fund or ETF can minimize. In addition, the DIY formulas avoid the expense ratios of fund managers. As a caution, the fact that all four strategies underperformed from 1998-2000 and again from 2018-2020 demonstrates that successful investing requires investor discipline. And finally, the fact that the effectiveness of these formulas has weakened in recent years demonstrates that markets are becoming more efficient over time (Andrew Lo’s Adaptive Markets Hypothesis), indicating the importance of continuous innovation in investing strategies.More By This Author:Artificial Intelligence and the Risks of Harking (Hypothesizing After-the-Fact)Forecasting Earnings, Artificial Intelligence (AI) Versus Equity AnalystsIntangibles And The Performance Of The Value Factor