Insights / ANALYTICS
How to Know if a Neural Network is Right for Your Machine Learning Initiative
TwitterInstagramLinkedInFacebook
INSIGHT
How to Know if a Neural Network is Right for Your Machine Learning Initiative
Author icon
by Frank Fineis

Deep learning models (aka neural nets) now power everything from self-driving cars to video recommendations on a YouTube feed, having grown very popular over the last couple of years. Despite their popularity, the technology is known to have some drawbacks, such as the deep learning “reproducibility crisis”— as it is very common for researchers at one company to be unable to recreate a set of results published by another, even on the same data set.

Read the rest of Frank’s post at KDnuggets.

RELATED INSIGHTS
WHITE PAPER
Lessons in Machine Learning: Optimizing Revenue
When it comes to balancing conversion and revenue, there is no free lunch: the two concepts are fundamentally at odds. This article looks at how you can optimize your site for revenue while maintaining or improving conversion.
Avatria Data Science and Analytics Team
READ MORE  
WHITE PAPER
How Far Do Customers Browse on eCommerce Sites? Not as Far as You Think.
An expression has been floating around that supposedly describes a painful truth of eCommerce shopping habits; it goes something like this: You could bury a body on page two, and no one would ever find it. It’s one of those ideas that feels right (when was the last time you clicked into the second page of search results for an answer?), but is much harder to find good data about. Fortunately, we have a lot of eCommerce data at hand, so we decided to try to dive into the question for ourselves.
John McDonough
READ MORE  
INSIGHT
Improve Conversion by Getting More Out of Your Search Engine
Did you know that over 70% of shoppers never make it to the second page of a product category and almost 90% never make it past the first page of search results? How many do you think even make it to the bottom of that first page? In today’s age, it is critically important that the products your customers are most likely to purchase appear above the fold on the first page. Customers expect you to show them what they’re looking for, and your margin for error is minimal.
Brian Ballard
READ MORE  
Have questions or want to chat?