Image: Deliveroo
Meals-on-wheels service benefits from a little data science and machine learning.
On-demand food company Deliveroo has revealed that a new algorithm it calls ‘Frank’ has cut delivery times by 20pc for its restaurants and riders.
Since setting up in Ireland two years ago, Deliveroo has proven pretty popular with takeaway enthusiasts, serving customers in Dublin, Cork, Galway, Belfast and Limerick.
‘We’re building an algorithm which can cope with millions of simultaneous orders’
– MIKE HUDACK
The ‘Frank’ algorithm is based on predictive technology that evaluates the most efficient way of distributing orders by location.
From field to fork
According to Deliveroo CTO Mike Hudack, machine learning is helping to predict the time it will take to prepare a meal, based on a specific type of order as well as on the time of day, all helping to streamline the experience from order to restaurant to customer.
“We’re building an algorithm which can cope with millions of simultaneous orders,” said Hudack.
“Our investment in the engineering team is testament to that ambition, and we are working on new, trailblazing technology that will make that ambition a reality.”
Hudack explained that the ‘nerve centre’ algorithm constantly looks at available riders and orders, then evaluates within seconds the most efficient way to dispatch them. After assessing all possible solutions, the algorithm decides which rider has the best characteristics to fulfil that specific order based on distance, type of location and other factors.
The result is that customers will get more precise details of when deliveries will arrive, with overall delivery times falling 20pc lower than they were in January.
Deliveroo’s Irish general manager, Liam Keenan, said: “Our new algorithm will continually refine itself, improving the experience for our Irish riders, restaurants and customers.”
