During my job position in FiloBlu, I was the person in charge to implemented CRO strategies and analyze all business data in order to get much more information to help all departments in the company to deliver better results (budget optimization, marketing strategies, AI merchandise, mail marketing automations, etc.).
I discovered CRO issues to deliver all the fixing necessary to uplift the conversion rate. One of the client I worked with was Lotto which it had some important UX issues to improve and it seemed to be a good challenging.

The Challenge

Analyze and solve UX and drop-off issues on the platform through analyze customer behavior navigation and purchase, to uplift conversion rate.

The Solution

To find evidence of the drop-off issues, I immediatly look at the quantitative data, into Google Analytics and after the qualitative; at first sight of the layout, there some UX euristic not respected, but for my personal inclinantion I always go deep into the data, avoiding bias and personal perceptions.

I was looking too a way to create an effective solution for a continuous website improvement, during the all departments job-journey in order to provide a better user experience by implementing a plan for a continuous conversion optimization.

Looking for some features indicators of customer behaviour, I create some new experiments to test some hypothesis, coming from the quantitative and qualitative analysis at my disposition:

  • "a bigger search text input would improve user engagement and conversions"
  • "people doesn't find the product they want"
  • "a simpler product merchandising would reduce abandonment rates"

To test the first  point, I created some A/B tests looking like as shown in the following pictures below.

The original version

The search bar was edited to deliver and enlight much more evidence in the head bar. A strong outline along the text input and the placeholder gives it much more evident and fits really nice in the e-commerce look and feel.

To show the search bar longer then before it was necessary to recreate the website categories: it was easy to simplify the main menu looking to the click insights and customer navigation pages. To perform better then a normal autocomplete search I implemented an external product which deliver a machine learning recommendations, based on customer previous navigations.

The A version of the test – it won and works much better than the other variants rolled out

Search bar with autocomplete intelligence engine

As you can see, in the following picture, I wrote "scarpe" (shoes) it's a general term but the search engine show me the most probably interesting results analyzing in real time my cookie.

This live search growed up the conversion rate more than 30%, only for sales coming from this starting point to checkout process.

Recommendation engine in the search bar

Personalization

The machine learning algorithm make us to create a more engaging user navigation, lowering the bounce rate (product, checkout, etc ..) and it reduced the abandonment rates, replacing some e-commerce section page.
Other important improvements needs more time to be delivered, such as implementing a complete visual personalized merchandising in order to create a real personal shopping experience, creating an hyper-personalization which deliver show a product based on customer behaviour, integrating other data sources too.

More engaged customers through machine learning recommendation engine.

I notice that it works really well when a user starts his purchase process in the search bar; in the product page, the cross-selling section works well too uplifting AOV (average order value) since in this phase because of the machine learning engine recommend good alternatives to current the product, fitting their needs and driving customers to checkout page.

Product Page

+200% uplift conversion rate

For all customer sessions which starting the purchase  only from the search bar

During the test the conversion rate increased by as much as 12.5%. On mobile devices, the performance was even better. The tested changes improved the mobile conversion rate by as much as 29%!

While all the updates had an impact, the new and improved shopping cart proved to be the biggest contributor to the uptick in conversions.

To translate these percentages into monetary terms, improving the conversion rate by 12.5% means the same thing as increasing revenue by 12.5%. So, if Lotto had monthly sales of 100,000 €, the increased conversion rate meant that they brought in an additional 12,500 € each month.

Not bad considering that it only took six weeks of working on to get these results.