This week, I’ll describe how ranking products can be problematic and show you a very quick and easy fix that many companies are unaware of.
I’ll start with a common scenario that surprisingly few companies get right. And the worst part? When you get it wrong it really hurts user experience. And poor user experience can be very costly.
Scenario:
You have a website with content that your users can rate with a thumbs-up or thumbs-down and you need to show the most-liked content up top. It’s the “show the most-liked content up top” part that I want to focus on. It’s subtly quite tricky to do this.
Say you have a product with 100 ratings, and out of those 100 ratings, 80 had thumbs up and 20 were thumbs down.
What’s the rating of the product?
Is it 80%? In other words, do 80% of all of your users really like this product?
The answer is, almost always, that we don’t know. Why not? Because we haven’t asked everyone yet. So that 80% is an indication of how well the product is liked, but there’s a vital piece of information missing…
Confidence
Confidence is everything! Let’s see why by using another example.
Say we have two products, A and B, and we need to rank them to show the best one at the top. (Of course, if we only had two products, the order wouldn’t matter much, but this technique extends easily to millions of products.)
Let’s say product A got 80 of 100 thumbs up. Let’s also say product B got 2 of 2 thumbs up. Which do you show first, A or B?
Well, B was liked 100% of the time!! And A was liked only 80% of the time. But how confident are we in each? Of course, we’re not very confident at all. Especially with B. It’s a bit like flipping a coin and getting two heads in a row. Does that mean that it’s a two-headed coin and we’ll always see heads? Probably not. So, what can we do?
What we need is a way of understanding how confident we are in each of these cases. And if we’re not very confident, we should put those items lower in a ranked list than highly-rated products that we have a lot of confidence in.
If this is interesting to you, please take a look here for exactly how to implement this confidence-based approach and start ranking your products or offerings confidently.
We’ve used this essential technique for Fortune 200 companies and early-stage start-ups. Don’t rank your products without it. It’s a game changer!
Of Interest
Why we Need to Start Teaching Artificial Intelligence
People often think of artificial intelligence as a mysterious black box. In truth, however, it surrounds us in many aspects of daily life. From rideshare apps and social media feeds to video games anticipating next moves and online chatbots answering homework questions, both adults and kids use A.I. technology every day. Yet many students and teachers alike do not understand what artificial intelligence is or how to talk about it, let alone teach it in the classroom. Here’s why we need to start teaching A.I.
Fawkes – a New Software Tool Developed to Cloak Your Images to Trick Facial Recognition Algorithms
The rapid rise of facial recognition systems has placed the technology into many facets of our daily lives. What might seem innocuous when Facebook identifies a friend in an uploaded photo grows more ominous in enterprises such as Clearview A.I., a private company that trained its facial recognition system on billions of images scraped without consent from social media and the internet. In response, a software called Fawkes was developed to “cloak” photos to prevent facial recognition. The software doesn’t make noticeable changes visible to the human eye, but enough to trick the deep learning computer models that power the facial recognition systems. Have a look yourself.
Amazon Wants to Make you an ML Practitioner – For Free
The tech giant plans to speed up machine learning (ML) proficiency by publicizing its long-internal material. Three courses have been released for immediate use: natural language, computer vision, and tabular data. More will be rolling out through the end of 2020, with the start of 2021 having all the material public. Read about it here.