Adobe XD exposing Design System
Recommendation Engine
A global technology company that specializes in providing IT infrastructure, cloud services, edge computing, security, and a wide range of other solutions to help businesses and organizations navigate the complexities of modern IT environments and drive innovation.
When users perused the product catalogue on the website, they frequently devoted an excessive amount of time to in-depth research and thorough product comparisons. Ultimately, the majority of users consistently opted to initiate direct contact, either through phone calls or our live chat function, seeking further insights into their desired product and soliciting personalized recommendations.
Undertake an extensive investigation to determine if the user journey through the product offerings can be significantly streamlined and made more user-friendly. The objective was to enhance the overall user experience, reduce the need for users to engage in lengthy research and comparisons, and proactively provide them with the information they require to make informed decisions.

During investigation, I conducted user surveys, analysed user behaviour on our website, and gathered feedback from customer service interactions. I identified key pain points and areas where users often encountered obstacles in their product selection process.
Recommendation engine serving 3K user on a weekly basis

In light of research findings and the commitment to provide exceptional personalized recommendations across various channels, Google's Recommendation Engine was implemented. This cutting-edge technology enables to deliver high-performing personalized suggestions, ensuring that each user receives the most optimal solution tailored to their unique needs.

The approach to personalized recommendations is rooted in the power of data analytics and AI-driven algorithms. By harnessing user behaviour data, the website can now proactively offer personalized product recommendations, enriching the user experience and simplifying the decision-making process.

The key distinction of implemented personalized recommendation system lies in its ability to engage with users selectively. It intervenes when a user exhibits uncertainty or indecision regarding the product they are currently viewing. Additionally, the recommendation engine evaluates users' behavioural patterns to determine the most appropriate and timely actions.

It's important to note that the personalized recommendation feature is designed to be accessible to a specific segment of users, ensuring that it seamlessly integrates into their journey while respecting the preferences and needs of all our valued visitors.

With the implementation of recommendation engine and thoughtful approach to personalized recommendations, the aim was to elevate the user experience, provide tailored solutions, and further optimize the user journey throughout our product offerings.

During the very first month after recommendation engine implementation, a gradual rice in the volume of users with recommendation engine loaded, viewed and clicked on was identified. 
8 weeks after implementation, the recommendation engine was serving to more than 3K users every week. Around half of them viewed the recommendation and 10% interacted with it.
Quantitative data
Quantitative Comparison
Quantitative data comparison

You may also like

Back to Top