5 Bandit Trials To Increase AdSense Profits

Our approach will be a 5-arm bandit test for these factors:

1. Left side vs right side
2. Above the fold vs. Under the fold
3. Embedded vs adjacent to content
4. Different ad sizes
5. Mobile vs desktop (separate configuration)

Before you start googling photos of older people doing bodybuilding, let me explain the analogy. Let’s start with why a bandit test gets its name, what it does, and how it will help increase the profit from your ads.

Have you ever seen slot machines in a casino? You put your money in, you pull a lever and you wait to see if you win something. Those handles are the “arms”. And the machine itself is the “bandit”. It’s no big secret that these machines steal from you blind, unless you own them.

How are Bandit Trials different from A / B Trials?

Let’s keep it simple. With A / B testing, you create two or more versions that you want to test. You send equal amounts of traffic to each one. At the end of the test, you choose a winner. From there, direct all traffic to the winning version. They call that “exploring” and then “exploding.”

However, there is a little problem here. During the course of the test, the losing variations are also getting a lot of traffic. That means they are wasting something.

So a bandit test still compares different versions. But you direct most of your traffic to the version that works best from the start.

You can try new variations like a / b tests, but reduce the amount of traffic sacrificed.

Eventual losers get less waste, and potential winners get more to turn into ad revenue.

“Explore” is the test variations part. “Explode” is perhaps a bit harsh. Because what it really means is leveraging your traffic in the best possible way.

Wait for another negative label. They call the bandits algorithm a “greedy” approach. But that’s just an industry term. It means that we want to focus our resources where we think we will get the best results.

Bandit Arm 1 – Left Side vs Right Side

Many UI designers will talk about the F and Z patterns. This relates to the way a user reads your page. A lot of research is done here. Researchers want to know where to focus. And they use eye or mouse movement tracking to find out.

Many web design templates provide navigation or advertising on the left or right side of the page. This also makes for a good testing opportunity for your ad units.

Where are they looking for more? Where do they click the most on the ads?

Bandit Arm 2 – Above the fold vs. Under the fold
You have heard the mantra “above the fold” for a long time. It started as an insistence:

Everything important on a page should be visible without scrolling.

But we have become wiser. Being above the middle or not is now a meaningful testing opportunity.

So we will also take that into account. How are your ad groups performing when they are placed in the top or bottom half of the page? Test it.

Bandit Arm 3: embedded vs adjacent to content

The traditional ad setup was to place ads in empty areas of the page. They could be within your header, footer, and side navigation. It was an attempt to keep them away from your main content. Beyond clutter, it also promotes a clear separation between content and ads.

Smart ad optimizers started thinking more deeply than just the F and Z patterns. If we expect the user to focus on the content, why not include our ad units in the content space? Embed them.

There is also adjacency. That is more like traditional ad placement. But the key here is exploring embedded content and other creative ways to place your ad units.

Bandit Arm 4 – Different Ad Sizes

Size may matter. But we just don’t know what size without testing. Almost all ad networks have different ad unit sizes and dimensions. There is a great variation. Compare traditional banners with skyscraper formats or video embeds.

Therefore, the type, size and dimension of the ads are also important factors for testing.

Bandit Arm 5 – Mobile vs Desktop (Separate Configuration)

This is the hot zone here. Mobile versus desktop. The use of mobile devices is exploding, as we all know. That means no serious web publisher can get it right in the long run without taking mobile traffic into account.

Separate apps are a bit out of reach here. But we can focus on testing standalone or responsive mobile versions of your site.

Responsive, the design and structure are designed to recognize mobile devices. When using the smaller screen sizes, the page layout and content may change. The design can change. Some content may even disappear.

In contrast, a separate mobile site setup is another version especially for mobile devices. With this method, you design a version that is only for target mobile devices. It is not linked to the responsible web version. It is designed specifically for mobile devices.

To implement these tests, start using AdNgin today. Or get more information first.