Notilyze participates in SAS EMEA Hackathon
We proudly announce the participation of Notilyze in the SAS EMEA Hackathon. The Hackathon will take place in February and the goal is to find a way to add sustainable value in real life business. We will take this challenge in cooperation with ELVA Community Engagement and the International Organization for Migration.
Yearly, 1.3 billion dollars of humanitarian aid funding is wasted due to outdated supply management practices in refugee camps (Van der Laan, 2016). As a result, an estimated 1.880.000 children, women and men per year cannot be provided with essential humanitarian supplies to keep them safe and in good health. Empirical evidence shows that this enormous human toll can be avoided through implementing better demand forecasting techniques within refugee/IDP camps.
Camp managers currently make use of ad-hoc, judgmental forecasting techniques, which are laboursome and comparatively ineffective. In contrast to our tool, existing AI-driven supply chain optimization tools however do not meet the needs of humanitarian missions as they fail to account for: 1) strong demand uncertainty due to conflict volatility; 2) SPHERE standards; 3) strong divergence of “product baskets” (i.e. foodstuffs, medicine, etc.) dependent on seasonality and camp location.
Camp Forecast (CF) will allow the distribution of life-saving humanitarian supplies, including medication, foodstuffs, blankets, tents and others, to an additional 1.880.000 children, women and men fleeing from conflict worldwide. CF will especially benefit children, pregnant women and IDPs/refugees with special needs – who are most vulnerable and dependent on humanitarian supplies within a camp setting. Keeping in mind the total humanitarian aid in 2017 amounted to 27.8 billion USD, an efficiency increase of 0.1% would already result in 27.8 million USD that could be utilized to better effect.
ELVA, the International Organization for Migration (IOM) and Notilyze have been cooperating to create such a Camp Forecast Tool. With this consortium we combine decades of leading humanitarian experience (IOM) with data collection, analysis and visualization experience in 20 conflict-affected countries worldwide (Elva Community Engagement) and strong commercial expertise building cutting-edge AI-driven supply chain solutions for commercial and non-commercial actors (Notilyze).
Until now this consortium has been focusing on simplifying the inventarisation of the stocks and the needs for the basic WASH supplies in camps. Instead of a monthly lengthy survey with questions on population, current WASH stocks and current needs a camp manager now only needs to fill out a number of people in the camp to get an estimate of the required WASH supplies and the costs coming along with these requirements (see Figure 1).
A disadvantage of IOM’s monthly “camp site assessments” as input for this forecast model is that data is available a month after the survey has been taken. To increase the quality of these forecasts an good estimate of the current population in a forecast is helpful. Therefore IOM would like to analyse other data sources that would help to gather more detailed data more efficiently and provide more accurate forecasts.
That is where we come in. Using satellite imagery we want to estimate the current amount of people in 50 refugee camps all over Nigeria. With this information we have both better input for the forecast model and we could revise our forecasts more quickly. Using SAS we want to build an operational object detection model to streamline estimations of camp sizes. The goal is to deliver insightful information on refugee populations with the SAS EMEA Hackathon 2020.
This goal perfectly fits the goal of the Hackathon, which is using data for good and linking the use case to the UN Sustainable Development Goals (see Figure 2).
van der Laan, E., van Dalen, J., Rohrmoser, M., & Simpson, R. (2016). Demand forecasting and order planning for humanitarian logistics: An empirical assessment. Journal of Operations Management, 45, 114-122.