I have often hoped to have an idea about the future, but when I predicted it, it was on the ground of (my) "todays" behavior. Whatever I did, thinking, modeling, .. machine learning. Predictive modeling tries to create models that forecast. It is a wavering calculus ...
We need to accept it: we often fail to predict the important stuff
The real behavior is often more complex than our models describe (if not, our models are reality). We need to embrace uncertainty.
But we can use scenarios to build resilience and agility
We learn to think in systems and if our constructions become better they build future.
This are the rough steps in quant finance: create models that have embraced uncertainty, solve them fast and correct, calibrate them to market data sets, test them across scenarios and benchmarks and if they become better, they build game rules to make the market a "known, when not fair, play".
And this is exactly what we have in mind with supporting quants: UnRisk for building future in the framework of their tasks. Over 70 working years went into bank-proof programmable tools. - and are available for present quants, who want to build future.
UnRisk often opens "this" or "that" alternatives that each lead to success. UnRisk Academy gives full explanation what is behind and individual actions to build and co-build groundbreaking things.
Thus, makes it easy to see a fork in the road and take one or another path knowingly ...
Picture from sehfelder