Intelligent Capacity Planning

Demand moves every week. Driver numbers do not. Build the engine that turns expected demand into the right drivers, in the right place, at the right time.

EMX is the logistics arm of the 7X Group — the delivery operator behind this challenge. What you build here has a direct pathway into EMX and the wider 7X ecosystem.

5 / 5slots taken

Dataset_AI-Powered Workforce Planning & Capacity Intelligence_Final.xlsx

Unlocks on event day

Track full — all 5 slots taken

The problem

Delivery companies can see roughly how busy the next three months will be, store by store. What nobody can work out is how many drivers that actually needs.

So the call gets made by hand. Planners estimate how many couriers each store needs, day by day and hour by hour. They decide when to start hiring, and when to bring in outside couriers instead. It rests on experience rather than data, and it misses the things that move the answer: some stores are simply more productive than others, some areas take longer to cover, and people take leave.

Get it wrong and it shows up fast. One store ends up overstaffed while another runs short. Costs climb on one side, deliveries run late on the other, and customers feel both. Hiring is the slowest lever of all, since a permanent courier can take two months to arrive. 7X is looking for a planning capability that turns expected demand into clear staffing and hiring recommendations, and keeps updating them as demand shifts.

What we're seeing

A rolling three-month shipment forecast already exists for every store. Nothing turns it into a staffing plan or a hiring decision.

Productivity, delivery times and route lengths vary a lot from store to store. Weekends are consistently busier than weekdays, and leave, days off and shift patterns cut into the capacity that looks available on paper.

The target mix is 60% permanent couriers and 40% outsourced. Permanent hires take 45 to 60 days to arrive and outsourced couriers 5 to 10, so the decision has to be made long before the demand does.

The numbers to move

95%
Match demand within 95% accuracy by store, day, and hour
20%
Reduce overstaffed and understaffed store-hours by 20%
95%
Achieve 0 store closures and above 95% on-time delivery through better rostering
AED 0.50
Cut labour cost per shipment by AED 0.50 while maintaining target courier utilisation & Generate hiring recommendations that reduce emergency recruitment

What a winning build looks like

Build a prototype that demonstrates measurable improvement in workforce planning accuracy over the current manual baseline using the provided dataset. Your solution should show how AI can turn a demand forecast into actionable staffing and hiring decisions — with clear reasoning behind every recommendation. Judges will evaluate based on the depth of AI implementation, how well the solution addresses the problem, technical execution, and real-world viability.