StarMine Models Identify Investment Factors That ‘Worked’ in 2014

A new year isn’t just for making resolutions. It’s also instructive to look back at the previous 12 months and see what factors “worked”. The StarMine team examines which factors performed well in 2014.

StarMine analyzed which factors worked well in 2014 by examining the performance of the StarMine models. We focused on a universe of the largest 3,000 securities in the U.S., largest 2,000 securities in Developed Europe, largest 1,000 securities in Developed Asia ex-Japan, and largest 1,500 securities in Emerging Markets. The results are purely out-of-sample and we ignored the impact of transaction costs in calculating returns. The portfolios were rebalanced monthly.

In the analysis, we included the StarMine Analyst Revisions model (ARM) which predicts future changes in analyst sentiment (earnings momentum) as well as the StarMine Price Momentum model. We also employed our two valuation models. The StarMine Intrinsic Valuation model (IV) uses a dividend discount model that accounts for optimism bias in the earnings growth projections. The StarMine Relative Valuation model (RV) is a stock ranking model that sorts companies by intelligently combining information from six powerful valuation ratios into a single comprehensive measure of relative valuation.

Investors tend to take advantage of the complementary information in value and momentum signals, so we therefore included the StarMine Value-Momentum model (Val-Mo). This model combines StarMine’s two valuation models (Intrinsic Valuation and Relative Valuation) with StarMine’s two momentum models (StarMine Analyst Revisions Model and StarMine Price Momentum) into a powerful stock-ranking model.

Also important to factor in is the StarMine Earnings Quality (EQ) signal, which is based on accruals, cash flow, and operating efficiency. When investors become more risk averse, they tend to put greater emphasis on these qualities. Finally, we looked at the StarMine Smart Holdings model (SH), which ranks stocks based on predicted future change in institutional ownership.

Strategic analysis

We examined a simple long-only strategy that creates portfolios from those stocks that rank in the top 10% of our universe, by each StarMine model. We looked at the trailing 12-month return, calculated as the difference between the top decile return and the equal-weighted average return (i.e., the market return).

With the exception of valuation models which didn’t work well in the U.S. and Developed Europe as well as the Earnings Quality model in Developed Asia ex-Japan and Emerging Markets, all the StarMine models performed solidly as part of a long-only strategy.

A strategy based on reacting to signals coming from analyst revisions (ARM), Price-Mo and the combined Val-Mo model outperformed the market in 2014 in all regions.

Considering individual markets’ performance (results not shown), Val-Mo worked particularly well in Brazil and Singapore where the model outperformed the market return by 9.7% and 7.0% respectively. In Canada, Price-Mo generated a return over the market of 11%.

Long-short strategy

For the benefit of investors that employ quant and equity long/short strategies, we also compared the StarMine models with the appropriate commonly-used quantitative factors that most closely approximate a simple alternative factor. You can see the results of portfolios formed from the StarMine models as well as the benchmark models, with the T12M decile spread plotted.

Momentum signals performed solidly across all regions in 2014. An investor using either the StarMine Analyst Revisions Model or building a basic revisions signal from the I/B/E/S estimates would have generated positive returns in the trailing 12 months in all regions. Similarly, price momentum signals generated strong performance in 2014 among all regions, with particular strength observed in the second half of the year.

In the United States, ARM and Price Momentum were among the best performing factors and significantly outperformed the results provided by the benchmark models. StarMine Price Mo, a price momentum signal that combines information from multiple dimensions of price momentum, significantly outperformed a basic price momentum model in all regions.

We also observed particularly strong outperformance in Developed Europe for the Val-Mo model, where the model has produced a decile spread of 36% in the trailing 12 months. Val-Mo was also the best performing signal in Developed Asia ex-Japan in 2014, yielding a decile spread of 24%.

Interestingly, rather than performing at a level of about the average of value and momentum, StarMine Val-Mo outperformed the best-performing individual signal in both Europe and Developed Asia ex-Japan. Therefore, a model with an intelligent blend of unique momentum and value signals, like StarMine Val-Mo, can give you the best of both worlds where the combination of the signal is greater than the average of its parts.

Although Earnings Quality struggled in Emerging Markets in 2014, momentum and value values performed solidly. StarMine Smart Holdings, which provides a unique perspective on utilizing ownership data, also performed well in the Emerging Markets region. Smart Holdings has also continued to perform particularly well in Developed Europe.

No factor works all the time, but it is clear that StarMine quant signals offer significant advantages over the commonly used alternatives in all global markets.

The table indicates the model’s benchmark used in the analysis.

Receive stories like this to your inbox as they are published. Subscribe here and follow us @Alpha_Now on Twitter. If you are looking to access our data or analytics, register for a free trial.