Skip to main content
All example use casesIllustrative example

Predicting medicine stock-outs across 40 dispensaries

A county health NGO wants early warning of essential-medicine stock-outs from monthly consumption reports.

The challenge

A county health NGO supports 40 dispensaries. Essential medicines run out before the next delivery, and staff only find out when patients are turned away. The team wants to predict stock-outs from monthly consumption reports.

Kind of support

  • Forecasting approach
  • Data readiness check
  • A simple model in a spreadsheet or Python
  • Handover to the team

How the mentorship could run

  1. Weeks 1 and 2: check the monthly consumption reports for gaps and errors, and agree which medicines to start with.
  2. Weeks 3 and 4: build a simple forecast for those medicines, starting with average use and lead time before trying anything more complex.
  3. Weeks 5 and 6: test the forecast against past months to see how many stock-outs it would have caught.
  4. Weeks 7 and 8: put the forecast in a spreadsheet the team can update each month, and train the staff who will use it.

What to have ready before you apply

  • Twelve months or more of consumption reports, even if incomplete
  • Delivery dates and lead times from the supplier
  • A list of the medicines that run out most often
  • Who can change an order when the forecast shows a risk

Risks to plan for

  • Reported consumption is low when stock has already run out, which hides real demand. The forecast should account for days without stock.
  • A complex model that no one can update will stop being used. A simple method the team understands is usually the better choice.
  • A forecast does not help if orders cannot change. Agree with the county team how a warning leads to action.

What a good result looks like

The team sees a likely stock-out weeks ahead, can request an early delivery, and turns fewer patients away.

More example use cases

  • Country: Bangladesh (Cox's Bazar)

    Sector: WASH

    Water-point dashboards with breakdown alerts

    A WASH NGO wants automated dashboards and alerts when a tap stand or latrine block stops working across 30 camps.

    Time: 1 to 2 hours per week, 8 weeksIllustrative example
  • Country: Colombia

    Sector: Cash assistance

    Finding duplicates across three cash programmes

    An INGO wants to find duplicate and likely wrong records across three programme lists, without building a surveillance tool.

    Time: 2 hours per week, 6 weeksIllustrative example
  • Country: Jordan

    Sector: Education

    Arabic reading practice with teacher review

    A learning centre wants an LLM to draft Arabic reading exercises, with a teacher checking everything before a child sees it.

    Time: 2 to 3 hours per week, 10 weeksIllustrative example
  • Country: Ukraine

    Sector: Shelter

    Building damage from drone and satellite imagery

    A shelter NGO wants to classify building damage from imagery so field teams visit the worst-hit areas first.

    Time: 1 to 3 hours per week, 12 weeksIllustrative example
  • Country: Nepal

    Sector: Information management

    A safe assistant over SOPs and guidance notes

    An information management officer wants to build a retrieval assistant over their organisation's SOPs, safely and on a small budget.

    Time: 1 hour per week, 8 weeksIllustrative example

Know more

Want to know more before you apply? Write to contact@theaiexpertgroup.com and a member of the Mentor Council will reply.