1. Introduction: AI for Food Price Forecasting in Humanitarian Response

According to the Global Report on Food Crises by the World Food Programme, in 2023, nearly 282 million people across 59 countries faced high levels of acute food insecurity. There is an urgent need for intervention, and to spend what funding is available as effectively as possible. Catholic Relief Services (CRS) uses machine learning and algorithms to predict food prices, enabling their programs to budget their needs more accurately and to procure food at the best possible prices. This case study explores how AI-powered market monitoring dashboards are transforming humanitarian decision-making, strengthening monitoring and evaluation (M&E) systems, and improving cost-effectiveness in international development.

2. Background: The Challenge of Market Monitoring

Aid for those impacted by food insecurity can be delivered through multiple modalities. While in the past the main approach was to ship food from the global North to areas in need, approaches such as cash and voucher assistance (CVA) and local and regional procurement (LRP) are viable alternatives that can provide assistance when food is available locally or when markets are functioning but suffer from lack of effective demand.

Across all modalities, CRS country programs need to continually monitor markets to confirm the continued appropriateness of their modality or procurement strategy and to inform programmatic and operational decisions. In particular, programs need to decide where and when to make food purchases, and how much cash is required to cover identified needs. These are not easy tasks, as food prices can be impacted by many factors at local, regional, and global levels.

3. AI Development: Building a One-Stop Data Shop

Previously, CRS country programs used manual processes and spreadsheets to support decision-making on CVA and LRP. This approach was complex due to the many different sources of data involved and had limitations in forecasting functionality and the ability to manage large amounts of data. What they wanted was a One-Stop Data Shop that would provide the information they needed in an easily accessible format.

To achieve this, the team needed to explore which data to use and how to use it, how to deal with the impact of seasonality on food prices, and which machine learning models would provide the best accuracy working on more than 15 years of historical data. They also had to determine an acceptable confidence interval to help country programs build appropriate price volatility buffers into their budgets. For some food commodities, the team found that prices were too variable to create reliable forecasts — in response, they created another algorithm to identify commodities with high price volatility.

4. Operationalizing AI: From Model to User-Friendly Dashboards

The team has to date developed a global Market Monitoring Dashboard, as well as regional and country-level dashboards. Apart from identifying and collecting local market data on food prices, a crucial part of implementation is ensuring users understand how to use the dashboards for decision-making. Collaboration is key: the dashboards are designed and developed as a partnership between technical and subject matter experts, leading to strong ownership by users while data analysts provide technical backstopping.

Feedback from users is positive: the dashboards save time versus earlier spreadsheet-based calculations and give credibility to the numbers presented. The dashboards also enable better business development, providing improved insights for building budgets for food security grants and highlighting risk areas where accurate forecasts are not possible.

5. Impact on International Development, Humanitarian Action, and M&E

6. Challenges: Measurement of Success and Technical Capacity

Working out more accurate measures of success has proven challenging. CRS would like to calculate savings made when procuring food based on the tool’s forecasts — however, this would require substantial input from country program teams who are already stretched and understandably prioritize their support to local communities. This highlights a common M&E constraint: the tension between rigorous impact measurement and operational burden on field staff.

Another challenge relates to infrastructure capacity. The team is currently working on improving the performance of the machine learning models so the dashboards can be rolled out to more countries. This includes optimizing model speed and scalability to handle larger datasets and more users across multiple country programs.

7. Key Learnings: Sustainability, Ownership, and Collaboration

8. Future Plans: Scaling and Sector-Wide Collaboration

Scaling the dashboards to additional regions and country programs remains a priority. The team continues to finesse the approach, improving the performance of machine learning models, addressing infrastructural bottlenecks, and exploring how additional analytics could provide further insights. The team is also adjusting to the new operating environment, exploring what data sources are available and how sector-wide collaboration on using data to address food insecurity can lead to increased impact.

9. Frequently Asked Questions (FAQ)