Deep learning and local maximums for recommendation engines

I wouldn’t consider this “light reading” but it’s super interesting to understand and consider.

“The clearest example of how that works is the increasingly ubiquitous recommendation engine. Almost every ecommerce site now lists other products that a visitor might be interested in while looking at an individual product. Figuring that those recommendations is an optimization problem, as the site owners want to show the items most likely to be add-on purchases for the visitor.

As it is approaching lunch time, I’ll use a food related example. Imagine a customer going to a grocery store web site and going to the page listing the different types of bagels that are available. A global optimization might notice that a very high percentage of people who buy bagels also buy smoked salmon. Therefore, the salmon is placed on the page as an added buy.

The problem is that all customers aren’t the same. The grocery site notices…”

https://www.google.com/amp/s/www.forbes.com/sites/davidteich/2018/10/17/management-ai-deep-learning-and-optimization/amp/

Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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