Incisively DOCS back to main site

Conversion Labs

Optimise virtually anything according to conversion rate.

The previously-described Promo Labs make it easy to optimise image click-through rate. But what if you want to optimise something else, like a piece of copy, a product ordering, or even a page layout? Or suppose you have a different goal, like maximising checkout conversions, or newsletter signups?

With just a little more work, you can use our Conversion Labs to optimise just about anything. This type of Lab is based on two simple concepts, suggestions and rewards:

  1. When you need an optimised value—e.g., displaying something to a user—you make a suggestion request to Incisively. The suggestion will tell you which value to use, and also contain a unique reward token.
  2. If the suggestion leads to a goal/conversion, you send the reward token back.

The suggested value is simple text, so it supports many types of values, including for example: headings, copy, URLs, CSS class names, template names, JSON, XML and CSV data.

Example: Generic Conversion Optimisation

In this example, we’ll be using the JavaScript SDK to illustrate the optimisation process. Other languages may look slightly different, but the process is the same.

Back at our imaginary jumper store, we aren’t sure whether customers respond best to products ordered by Price, Popularity or Customer Review Rating. Imagine our website currently uses the following line of code to set the order of the products:


Let’s see how we could use Incisively to optimise the ordering for best checkout conversion rate.

Step 1: Create the Lab & Variants

Log in to the Incisively Web App, select the “Conversion Optimisation Labs” tab, and create a new Lab called “Product Ordering”.

Again, click “Edit Lab” and then “Add Variant” to input each of our proposed orderings. Conversion Lab variants only have “Name” and “Content” fields, so fill them in like so:

Name Content
Price price
Popularity popularity
Review Rating review_rating

Turn the Active switch on for each Variant, and the Lab is ready to go.

Step 2: Implement suggestion code

When it’s time to order the products, we ask Incisively for a suggestion, and use that value to order our products. All we need is our account ID (let’s imagine it’s 1234567) and a Lab ID, which we get by clicking ‘Edit Lab’ in the Web App (let’s imagine that’s 11111111-2222-3333-4444-555555555555).

Here’s our new optimised product ordering code:

var incisively = new Incisively(1234567);

  lab: '11111111-2222-3333-4444-555555555555',
  success: function(suggestion) {

All we had to do was replace the string 'price' with the variable suggestion.content from Incisively, since we know this will be price, popularity or reward_rating.

Step 3: Implement reward code

In order to learn how each variant is performing, Incisively must be informed when a suggestion successfully influences a user to take the desired action (e.g. make a purchase, or click a button). You do this by sending the user’s reward_token to the Reward endpoint.

In our example, we want to optimise the checkout conversion rate, so the Payment Complete page would be an ideal place to send the reward token:

var incisively = new Incisively(1234567);
  lab: '11111111-2222-3333-4444-555555555555'

Step 4: Up and running

Now that your Lab is working, there’s nothing else you need to do. The algorithms will constantly monitor performance and adjust suggestions accordingly.

If you like, you can see what’s going on by clicking View Performance next to your Lab’s name in the web app.