It’s a common sight to see a line of green jackets outside eateries at mealtimes, as our delivery-partners arrive and wait to pick up orders. But we’re working to make pick-up more and more efficient for our merchant- and delivery-partners, to shorten those lines.

From the moment a user orders a dish, our system optimises to assign the correct delivery-partner for pick-up. This doesn’t simply mean assigning the nearest one to the job, because a delivery-partner waiting outside while the food isn’t ready yet is a waste of time that could be used to pick up another order. Yet, we don’t want a delivery-partner coming later while the food is sitting out there getting cold.

The “Goldilocks” pick-up window

The business of getting our delivery-partners to arrive at restaurants at the right time requires our machine learning and predictive analytics engines to figure out when we should assign a delivery-partner to head towards the restaurant.

Our engineers refer to this sweet spot the “just-in-time” window. The Grab system calculates this based on multiple factors such as the time taken for food preparation, an estimate of how long it would take to assign an order to a delivery-partner as well as the time taken for delivery-partners to get to the restaurant and pick up the order.

Ideally, the order should be ready as soon as our delivery-partners arrive at the F&B outlet.

Our engineers call this sweet spot the "just-in-time" window.

Previously, F&B merchants would only begin food preparation once a delivery-partner had been assigned to the order. But depending on the size and type of order, some merchants may need more time.

The buffer time before allocation, which is calculated based on food preparation time, will give merchants the headstart that they need to prepare orders. 

Smaller orders that require less time to prepare will see a shorter buffer time before a delivery-partner is assigned. On the other hand, there will be a longer buffer time before a delivery-partner is assigned to larger orders.

This will ensure that delivery-partners arrive at the store as soon as the order is ready for pickup, rather than too early or late. 

After we rolled out improvements to the system, the average wait time for delivery-partners across the region was trimmed to 5.6 minutes in the third quarter of 2022, down from 6.4 minutes the previous quarter.

Accurate predictions

But for our calculations to work, it was important for us to ensure that we are able to accurately predict food preparation times. 

To do this, we turned to our merchants to help us gather more data on food preparation times. We introduced an in-app feature which prompts merchants to mark orders as “ready” once food is ready for collection. 

The data gathered fine-tunes our system to better predict the actual time taken for food preparation across different types of orders. 

The system also learns to differentiate orders that require a delivery-partner to come quickly from those that can wait a little longer.

Komsan Chiyadis

GrabFood delivery-partner, Thailand

Komsan Chiyadis

GrabFood delivery-partner, Thailand

COVID-19 has dealt an unprecedented blow to the tourism industry, affecting the livelihoods of millions of workers. One of them was Komsan, an assistant chef in a luxury hotel based in the Srinakarin area.

As the number of tourists at the hotel plunged, he decided to sign up as a GrabFood delivery-partner to earn an alternative income. Soon after, the hotel ceased operations.

Komsan has viewed this change through an optimistic lens, calling it the perfect opportunity for him to embark on a fresh journey after his previous job. Aside from GrabFood deliveries, he now also picks up GrabExpress jobs. It can get tiring, having to shuttle between different locations, but Komsan finds it exciting. And mostly, he’s glad to get his income back on track.