The predictive power of a scientific theory refers to its ability to generate testable predictions.
Scientific ideas that do not confer any predictive power are considered at best “conjectures”, or at worst “pseudoscience”. Because they cannot be tested in any way, there is no way to determine whether they are true or false, and so they do not gain the status of “scientific theory”.
In other words, a scientific theory must be testable. If you are unable to test the belief, you don’t have a valid theory.
For example, applying this to portfolio management means that you must have been able to test your strategy to earn scientific evidence. If you buy at a certain signal and sell at a specific signal, if you are unable to test how the signals worked (or have enough actual performance) you are unable to prove the signals have any usefulness for generating profit: predictive power.
Predictive power or predictive ability is gained by testing to discover if it does have predictive ability. One can test a strategy over a long period by trading it in real time, but that may be an expensive way to determine predictive power if it is found it isn’t profitable. This is the value of proper quantitative testing of systems with a scientific process, which is what we do at Shell Capital Management, LLC.