This is from one of my favorite websites, Data Mining and Predictive Analytics: Random things... The writer writes about randomness - and two of the books that I have read, Nassim Nicholas Taleb's "Fooled by Randomness" and "The Black Swan". Here's a snippet:
I personally don't agree philosophically with the role of randomness. (I would prefer to say that many outcomes are unexplained then say randomness is the "reason" or "cause"--randomness does nothing itself, it is our way of saying "I don't know why" or "it is too hard to figure out why").
The writer also suggests some ways around it:
The solution? One great help in overcoming these problems is through sampling--the train/test/validate subset method, or by resampling methods (like bootstrapping). But having the mindset of skepticism about models helps tremendously in digging to ensure the models truly are predictive and not just a random matching of the patterns of interest.
To which I agree.
There must be some explanation for things that are happening around us. There are "black swans" that are very unlikely to happen, but when they happen, result to catastrophic results. But these, too, could be managed if one were to expand his/her horizons and be truly duly-diligent (and well, border on paranoia).
However, there is something that is confusing me a bit: Is it really possible for us to predict with absolute certainty that we can predict the future? Is it really possible for us to measure every single thing - and thereby explain every single thing that we encounter in the "real world"?
A part of me wants to say "yes". Yet still, a part of me wants to say "no".
There are a lot of techniques out there that can minimize projections and come up with models that could even model these errors and the likelihood of these errors. But are we ever really going to be certain? Are we ever going to be absolutely certain?
