Smallholder farmers are among the most vulnerable communities in developing countries due to poverty and social exclusion, lacking a stable income due to inconsistent access to markets. Aiming to tackle rural poverty, Brazilian government established institutional markets for smallholder farmers to supply their produce to schools through a non-competitive bidding mechanism. Participation of farmers to these institutional markets remains still limited due to challenges in the evaluation of the profitability of participating to each call of the bidding mechanism and in the planning and coordination of the distribution activities. A decision support system (DSS) was developed to guide farmers on the different stages of the institutional markets participation, including the definition of the optimal strategies for bidding and contract acceptance, as well as the optimisation of the distribution activities through a Heterogeneous Fleet Split Delivery Vehicle Routing Problem, aiming to maximise the profits for farmers. The DSS was applied to the case study of Canudos settlement (Goiás state) and is progressively being embedded in Progressive Web Apps to maximise its real-life impact. The proposed approach has a significant social impact for 1.5 million vulnerable smallholder farmers in Brazil and can substantially improve their living conditions by providing security of income and reducing poverty, thus strengthening inclusive agricultural growth.

The Organ Procurement and Transplantation Network (OPTN) is overhauling its organ allocation policies in a generational change, aiming for more efficient and equitable outcomes. We introduce a novel analytical framework to enable dynamic exploration of the efficient frontier of policy options. Jointly with OPTN, we applied our framework to the design of a new allocation policy for lungs, which was eventually approved for implementation. From 2023, all lungs in the U.S. will be allocated according to the said policy, projected to reduce waitlist mortality by >20% compared to current policy. (joint work with Ted Papalexopoulos, Dimitris Bertsimas, James Alcorn, Rebecca Goff and Darren Stewart)

Wildlife poaching fuels the multi-billion dollar illegal wildlife trade and pushes countless species to the brink of extinction. To aid rangers in preventing poaching in protected areas around the world, we have developed PAWS, the Protection Assistant for Wildlife Security. We present technical advances in multi-armed bandits and robust sequential decision-making using reinforcement learning, with research questions that emerged from on-the-ground challenges. We also discuss bridging the gap between research and practice, presenting results from field tests in Cambodia and large-scale deployment through integration with SMART, the leading software system for protected area management used by over 1,000 wildlife parks worldwide.

We are organising a launching conference to bring together our key partners, researchers and (potential) sponsors. Our aim is to inspire each other, share ABW’s vision and plans and explore opportunities for collaboration.

In this seminar we will review emergency medical response vehicle location models and dispatch algorithms with a focus on ambulances on wheels and helicopters.

This session explores the use of remote sensing, geospatial analysis and artificial intelligence to provide novel geospatial insights for increased operational efficiency and data-driven transparency.

Centralized diagnostic networks play a critical role in the delivery of essential healthcare services in resource-limited settings. We propose a two-part system that uses a low-cost, feature phone data sharing platform to monitor sample volumes at healthcare facilities, and an optimized sample transportation model to generate efficient routes for ST couriers on a daily basis. Since implementation, the proportion of unnecessary courier trips has been reduced by 55% and average ST delays have been shortened by an estimated 25%.

NeatWork is an optimization and simulation tool for the design of water-distribution systems with the aim of providing clean water to poor rural communities.

This talk describes the implementation of data- and analytics-driven innovation in health systems. In particular, it is focused on innovation around operations, system design, and optimization of large delivery systems.

In this webinar, we highlight the benefits of analytics in assisted door-to-door travel on long distances for elderly and disabled people.

In this lecture we will discuss analytics contributions to address the main challenges in cancer diagnosis and treatment: 1. Localizing the tumor, 2. hitting the tumor but not the surrounding healthy organs-at-risk (OAR), and 3. individualizing the treatment approach and “optimal stopping”. We will focus on radiation therapy, one the main pillars of cancer treatment and arguably the most quantitative cancer specialty.

In this webinar we will highlight Tilburg University’s (The Netherlands) work at the United Nations – World Food Programme (WFP) headquarters in Rome