Recommendation Engine: How to get it right with A/B testing.

Did you ever wonder how Netflix makes you binge watch a whole series which eventually becomes your favorite? How about the way e-commerce websites like Amazon use the rather famous “Customers Who Bought This Item Also Bought” trick? Now, just imagine if you got to apply these methods to your website. How impactful would that be?

All this could be possible with the help of a “Recommendation Engine”.

This is the best way to offer a user-friendly service to ensure customer satisfaction which eventually results in higher revenue. Just like Amazon or Netflix.

Most websites don’t use this feature due to its complexity. It is also difficult to judge whether to apply it permanently or not. What if there was a way through which you can test it beforehand and make sure it will be worth it? Having said that, I mean that you must apply recommendation system on your site, right now, through A/B test. This will help you decide if you need a recommendation engine or not, as it provides the comparative stats of conversion hikes before and after.

A/B test is not a new term, smart websites have been using it for a long time. There are many tools which help in developing a nice A/B test. We, and many others, use tools like Optimizely, Adobe Target, VWO and Google Optimize to build successful tests.

To discover more about this, let’s first learn about a recommendation engine.



 

What is recommendation engine?

As the name suggests, it’s a recommendation engine or system which works as an agent to connect the products and services of your website with the nature of the product a user is already interested in, based on what another user with similar behavior did, or on a popularity basis of the products of same genre, etc.

For example, whenever we do online shopping, we either purchase something we like or something recommended to us by others because we trust that person. A recommendation engine works like that person for online shopping. The suggestions shown can be a result of the list of the complementary products you want to show along with the main one, which we will use and apply in your recommendation engine. It is basically a way to use the data you already have to work in favor of you.

Here I added Television in my cart from BestBuy, now instead of showing me another T.V the recommendation system suggested me the options of wall mount and sound system, which are necessities to have for a television. Pretty smart move right? All you need is to add this feature on your site with the help of good web experts.

Why do you need recommendation engine?

Online shops need recommendation engine as a marketing strategy because if you set it up properly, it will surely boost conversions, CTR, and revenues.

  • It helps the website to change its way of communicating with the customers.
  • It helps you to promote your product to your potential buyers.
  • It increases the sale as the user can buy two or more items instead of one because of the recommendations.
  • Enhance your consumer satisfaction graph by providing personalized service to every client.
  • To save time and money.
  • To increase revenue by using potential resources.

Is recommendation engine for you or not?

This feature is for all the e-commerce based websites which provide a large number of related products. This is to increase the order value of the customer by letting them add related products they might need. Which is slightly different from upselling and cross-selling, as it is not only about price, but focuses on customer’s taste, which is obviously a better approach to sell. However, if you have a website which serves only one or two unique products, then it is not necessary for you to own this feature on your website as it will be of no use. Strollik is a single product based website which does not need a recommendation engine. However, if your website offers more than one product, then you must go for it.

I don’t know if you are aware or not but Amazon credits 35% of its revenue to its recommendation system. They show a user the items which are purchased along with the items that a user has in their cart, or the products similar to the ones they already viewed, etc.

How to evaluate and measure the recommendation system? (with the help of A/B testing)

Like any other step in the e-commerce world, the recommendation system also needs some kind of analysis before applying it. The best way to know that is to do A/B testing, which will help you to know whether recommendation engine will give you more clicks, sales, and increased usage or not.

A/B testing is the best way for online user evaluation. Let me explain to you with an example; we at Brillmark have the clients who ask us to create a recommendation system for their website with the help of A/B testing.

For Example:
Sometimes clients ask us to build a recommendation engine for their website, but they are unaware of the fact that they are the ones who have the data with them to know which products can give more conversions.

Optimizely overall revenue result
Optimizely Overall Revenue Result

Optimizely cart result page visit result
Optimizely Cart Result Page Visit Result

As you can see in the above data the A/B testing allows you to judge the result between original and variation. The data shows clearly what effect a change can or cannot give to your website if shown live.
You will get more results about the related effects to RS which are cart conversions, thank you page improvement, order review growth etc. Now you know how can A/B test plays an important role in decision making.

So, it is our job to let them know that by building an A/B test for them. We use their list to apply in recommendation system which we run on the live site, we compare your site with and without RS to show you RS’s conversion power. Pretty simple, right? You just need a good team like us and you will be good to go with your RS.

The process is simple. You will give us a list of products that you want to show with a particular product, we apply the same in RS designs, to run an A/B test. We run the RS A/B test variations on live site for a day or two, once we will get the results about conversions because of RS, we apply that hero to your live site. It’s pretty basic but it needs a lot of research and knowledge to create an ideal RS for higher revenue.

Are you wondering why we should run A/B test and not apply the RS directly? It is because, sometimes, putting a recommendation engine on cart page may redirect the customer to other products which could kill the chances of a sales. So, in order to be sure before the implementation, we can see the result from the A/B test and decide based on its stats.

We have to be sure when it comes to increasing sales and numbers, which should always go up.

Now you know how to increase your user-base, clicks, and provide better personalization to each of your users in an effective manner. It can be the most useful technical and financial investment you can do for your website. A good quality A/B test and best recommendation engine can elevate your business to a whole new level. You just need to find the right web experts to do that for you.

We at Brillmark promise you to provide that, in the best way possible. We hope to work with you soon.