Forecasting benchmarks of long-term stock returns via machine learning
Research into machine learning techniques finds potential benefits for long-term saving strategies.
Recent advances in pension product development seem to favour alternatives to the risk free asset often used as a performance standard for measuring the value generated by an investment.
To this end, for the paper Forecasting benchmarks of long-term stock returns via machine learning, the simplest machine learning technique was applied to forecast stock returns in excess of different benchmarks, including the short-term interest rate, long-term interest rate, earnings-by-price ratio, and the inflation.
The researchers found that, net-of-inflation, the combined earnings-by-price and long-short rate spread formed the best-performing, two dimensional set of predictors for future annual stock returns.
This is a crucial conclusion for actuarial applications that aim to provide real-income forecasts for pensioners.
The working paper is available for download at the link below.
