top of page

First basket by using personalised recommendations

GOAL: How we improved our first time customers experience

First Favs design - tumbnail 1024x768.jpg
First Favs design - learn 1024x768.jpg

PROBLEM SPACE

First Favs design - scope 1024x768.jpg

RESEARCH & INSIGHTS

User desires...

1. Browse and compare products

2. Build basket quickly

We kicked-off this project during the pandemic, as a lot of the customers where buying their products online. One of the biggest pain point was costumer having to build their basket for the first time (average 60+ items from scratch). As a new customer you land on a website, everything is new and you need to learn new patterns, behaviour to get to what you need. With the time constraints ever pressing, we ran a scope meeting to narrow down what we could realistically deliver before December 2020.    

HMW

How might we help the user to build up their basket using personalised recommendations?

Reducing scope

In collaboration with a Google researcher and the Sainsbury’s research team, we ran a 250-user survey to understand how first-time users were building their baskets. Also, we tested with customers several UI and different heading copy to identify which would be easier for the customer to use and make easier to understand for first-time customers. 

Insights

  • Users spend a lot of time trying to find the products they need. 65% search for specific products. 

  • Recommendations were clear and the user quickly proceeded to checkout

First Favs design - user stories 1024x768.jpg

UI/UX DESIGN

First Favs design - MVP 1024x768.jpg

VALIDATION

User Journey, wireframes and prototypes

Some hypothesis were discussed internally and narrow down with different stakeholders as time was a constrain and had a big impact during the pandemic with Feed the Nation programme (read more here). We then decided to build an A/B test to validate it. 

Challenges

  • The pandemic and trying to serve as much users as possible in a short period of time.

  • Users were not Tech-Savvy and struggled to build their first time basket.

  • Loosing users cause of current onboarding experience. 

Validation and measure of success

We reviewed data to see which were the current most popular items and used AI to start building those recommendations over time. Users will land on a recommendation page after onboarding and select a variety of products to quickly build their basket. 

A/B test current experience vs AI Google recommendations:​

  • Improvement in conversion with the AI compared with
    the current experience

  • Quicker building basket by 5%

Medium Article here

First Basket personalisation
bottom of page