AI for Uganda's Informal Economy

Course outline and learning expectations

This is a tutor-led course. The outline shows what your tutor will cover; teaching materials and examinations are provided directly to enrolled students.

What you will learn

• Explain the data challenges and opportunities within Uganda's informal economy
• Prepare incomplete, manually recorded or location-based data for responsible analysis
• Build and evaluate demand-forecasting models for informal traders
• Develop route and pricing optimisation logic for boda-boda and delivery services
• Analyse market-price patterns and communicate uncertainty without misleading users
• Create an inventory-prediction tool for a small shop
• Design a low-bandwidth AI service prototype for USSD or SMS access
• Apply privacy, consent, data-minimisation and human-oversight principles
• Test an AI tool for usability, trust and adoption among intended users
• Build and present a boda-boda demand-prediction and smart-pricing capstone prototype

Modules

1. 1

   Understanding Informal-Economy Data Challenges

   Examine how data is generated, recorded and used by boda-boda operators, market vendors, small traders and neighbourhood shops

   Uganda's informal-economy contextData availability and qualityManual and cash-heavy recordsSeasonality and location effectsEthical data collection
2. 2

   Demand Forecasting for Informal Traders

   Build practical forecasts that help traders estimate customer demand while communicating uncertainty

   Forecasting questionsTime-series featuresSeasonality and eventsBaseline modelsForecast evaluation
3. 3

   Route and Pricing Optimisation for Boda-Boda and Delivery

   Develop decision-support logic for route choice, estimated demand and transparent pricing

   Location data preparationRoute constraintsDemand by time and placePricing factorsFair and explainable recommendations
4. 4

   Market-Price Prediction and Price-Difference Insights

   Analyse price movements across markets and locations to support better purchasing and selling decisions

   Market-price datasetsTrend and seasonality analysisPrice predictionLocation comparisonsUncertainty and limitations
5. 5

   Inventory Prediction for Small Shops

   Create a simple stock-planning tool using sales, stock and replenishment records

   Inventory data preparationDemand and lead-time featuresReorder indicatorsStock-out riskSimple dashboards
6. 6

   Designing for USSD and SMS Access

   Prototype AI-supported services that work on feature phones and low-bandwidth connections

   USSD interaction flowsSMS message designShort-session constraintsLocal-language and accessibility considerationsMock testing
7. 7

   Trust, Responsible Data Use and Adoption

   Design tools that intended users can understand, question and use safely

   User-centred researchPrivacy and consentData minimisationExplainabilityHuman oversightPilot testing and feedback
8. 8

   Capstone — Informal-Economy AI Tool

   Build and present a boda-boda demand-prediction and smart-pricing prototype using time-of-day and location data

   Problem definitionData preparationForecasting modelPricing logicUSSD/SMS or dashboard prototypeResponsible-use reviewPresentation