/biz/ - Business & Finance

I know you retards aren't going to have anything to say about this but I will ask anyway.

How do you estimate the expected return for an asset class for the next month?
As opposed to the next eternity. Which is what you are doing when you take a mean of historical returns.

This is an important question because, sure if I buy the SPY and hold it for 5 decades my return might be about 7%. I'm comfortable making that estimate. But to say the expected return over the next month is 7% p.a. is absurd.

I have three (or more) potential methods I am considering
>Using a moving average, then calculating the uncertainty of the estimate and then making my investments risk-adjusted to the measure of returns.
>A model which is based on both a moving average and the Buffett indicator.
>A model which is based on a total average and Ray Dalio's 4 economic cycle theory
I am hesitant to use any method based on fundamental analysis because as the saying goes, the market can stay irrational for longer than you can stay solvent.
I could also set up a Bayesian optimization which just throws every machine learning algorithm at it.

I already have a good model for expected volatility.
But the optimization problem of allocating my resources can't be solves unless I have an expected return estimate.