Experts beat by very simple algorithms

When it comes to prediction in anything. It is usually the most simple algorithm with the fewest moving parts that can stand the test of time.

But there’s an aspect of this axiom that is even more fun. Experts often tout their ability to predict the future in various fields. Recent research concerning experts versus simple algorithms has shown that this is often not the case.

The best example in my reading is a wine connoisseur who buys and sells wine of a particular region in France each year. Not only does the algorithm (which simply uses rain fall and temperature to achieve a forecast price with 90% accuracy)  beat the expert, even when the expert has the ANSWER from the algorithm and is told the algorithm’s ACCURACY, he still forecasts worse than the algorithm.

It is mostly due to humans natural tendency to overweight minor details. The expert tries to think outside the box and be smarter.

So what’s the big deal? Well if you’re a wine connoiseur, shut up and trust the algorithm and if you’re in business, look for ways to use simple algorithms where your judgement might be clouded by several small confounding factors whose weight you’re likely to overvalue.

More interesting things to come from Kahneman’s new book, I’m sure.


Leave a comment

Filed under All posts, Business

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s