27% increase in sales
achieved within just 30 days.
Who are you?
Formerly Motoring.co.uk, Regit is the UK’s leading online service for drivers. Working with Peak, we’ve been able to predict which of our 2.5 million users are going to change their vehicle and when. It means we can serve our customers in a more personalized and targeted way and has increased our call center revenues by more than a quarter.
What was your challenge?
There are two parts to our service: we generate leads for companies in the automotive industry by providing a way for people to book test drives, buy and sell cars and request brochures, among other things. We could not predict which of our users were likely to change their vehicle, or even know who had changed their vehicle until after it had happened.
Through our subscription to Peak's service, we have gained a cutting-edge data analytics capability which has enabled us to drive a 27% revenue growth through our call center. We couldn’t be happier with the results – we are actively recommending Peak to third parties.
What did Peak do?
Using Peak’s AI platform they pulled together our user data with data from our website and marketing systems, as well as from the DVLA (Drivers and Vehicle Licensing Agency). They applied ‘Categorical Machine Learning models’ that can handle both category and variable data simultaneously. It gives predictions about the likelihood of users changing their vehicle — resulting in a sale for Regit.
The Peak platform utilizes AWS SageMaker to deploy machine learning models, with the platform creating a simple ‘lead-score’. The lead scores are then pushed into our CRM system, allowing our call-center agents to prioritize their activity based on the users with the highest chance of converting to a sale.
Categorial machine learning is a type of AI that allows computers to learn something through experience, testing, and adaptation, rather than having been explicitly programmed in the first place.
What’s the upshot?
Working with Peak, we’ve had a 27% increase in sales. We’ve also been able to reduce operational costs by up to 35%. We now staff the call-center at optimal times of day where we’re most likely to result in a sale to a user or customer. We’re now offering improved services to our customers, increasing their satisfaction levels and growing our revenues in doing so.