Agent Computing and AI to Achieve the 2030 Agenda: New Methods to Infer Policy Priorities from Open Fiscal Data and Sustainable Development Indicators

How can we reach the Sustainable Development Goals (SDGs) by 2030? This is the most recurrent question in most international forums, and a central factor in how governments are formulating policy priorities around the world. However, how can we know if those priorities are conducive to the SDGs? Will developing countries repeat the same mistakes from adopting the Millennium Development Goals (regarded by many scholars as a failed agenda)? How can we improve the way in which governments formulate policy priorities? This project will harness novel data on public expenditure and development indicators, cutting-edge machine learning techniques, and state-of-the-art computational simulation methods to tackle these questions. In doing so, it will produce profound insights into how governments prioritise policy issues, and redraw the landscape of questions and methods that guide evidence-based policymaking.

The project is structured in three pillars: (1) linking public expenditure data to SDGs, (2) identifying development indicators that are susceptible of direct policy interventions, and (3) modelling the process of policy prioritisation to assess development strategies. The first pillar builds on the growing movement of open fiscal data. The idea is to classify public expenditure programmes into the SDGs through deep learning. To train this classifier, I will employ a novel dataset from Mexico (unique in the world), in which government experts have assigned SDG labels to 4,000 expenditure programmes. This is the same technology used by Netflix to classify movies. Since hiring movie experts to categorise every movie is economically unfeasible, the company uses a sample of expert classifications, and exploits the texts describing the plots to train an algorithm and predict labels. In a similar way, I will exploit the texts describing Mexican expenditure programmes in order to assign SDG labels to unclassified data.

The second pillar consists of identifying development indicators that are 'instrumental'. These are indicators susceptible of being intervened by specific policies that receive dedicated resources. For example, a vaccination campaign (a policy with resources) is designed to transform the indicator of incidence of measles (the indicator). Interestingly, there exist several development indicators that are not instrumental. For example, GDP per capita is a composite measure of various factors and no government has a specific policy to directly intervene on it. Thus, identifying instrumental indicators is key to understand and evaluate policy priorities, as governments only allocate resources to those development issues with policy instruments. I propose conducting an online survey across policymakers and experts who will be asked to identify instrumental indicators from a random sample. With the support of the UNDP and GIFT, this survey will be administered to UNDP functionaries and government officials around the world. Through this survey, I expect to classify approximately 100 to 150 development indicators.

The third pillar builds on 1 and 2 in order to calibrate an agent-computing model of policy prioritisation. I have previously developed a similar model and validated it throughout various publications, for example, by estimating policy priorities, policy resilience, policy coherence, ex-ante policy evaluation, and the effectiveness of the rule of law. A distinctive feature of my model is that policy priorities (in the form of resource allocations across development indicators) emerge endogenously from an adaptive policymaking process that takes into account the complex network of interlinkages between SDGs (a central topic in the sustainability literature). Thus, these priorities can be defined over instrumental indicators, and the model can be calibrated to match the empirical expenditure patterns estimated in pillar 1. There is currently no tool that can achieve this.

The project has an enormous potential for worldwide impact. As I write this proposal, I am running a project -in collaboration with the UNDP- to advise the Mexican government on policy prioritisations that are consistent with its national development strategy. This project, however, does not consider fiscal data, as linking expenditure to SDGs is a monumental task on its own (hence my application for this fellowship). Nevertheless, the potential impact of the computational tools that I have developed has already been recognised by important policy actors. For example, the UNDP regional director for Latin-America and the Caribbean said -in our first workshop- that the Policy Priority Inference touches exactly on the issues and questions that all governments are facing with the 2030 Agenda. Furthermore, in one of my presentations to the UNDP, the director of the Human Development Report Office -Pedro Conceição- expressed his familiarity with agent-computing models (employed during the Ebola outbreak), and mentioned that my approach to study policy priorities has enormous potential to address questions that no other method can. Finally, my method was recently mentioned in a visible publication in Nature (Margetts & Dorobantu, 2019). These examples portray a strong institutional backing, and a tremendous potential for high impact.

Within the project pillars, I identify three important outputs. First, the fiscal-SDGs linked database will be an extremely valuable asset for policymakers, consultants and academics, even if they use more traditional tools of analysis. These data will allow better estimates on the impact that expenditure has on development indicators. The second output will come from the online survey of instrumental indicators. With this, governments will be able to establish more realistic development goals. Moreover, knowing which policy issues lack instruments and resources could ignite transcendental public debates in many countries. The third output is the agent-computing model. This tool, in the form of an online app and an R package, will be extremely useful to technical teams of different governments and international organisations. While the package will facilitate systematic ex-ante evaluations of development strategies, the online application will allow to better communicate government's policy priorities to a broader audience.

Besides the institutional support from the UNDP, there will be great impact from collaborating with the Global Initiative for Fiscal Transparency (GIFT). This organisation actively engages with governments to persuade them in making their expenditure data publicly available. The project outputs will provide GIFT with attractive analytic tools that exploit open fiscal data. For example, showing a minister how the agent-computing model can be calibrated with his/her data, in order to estimate coherent policy priorities, is clear proof of the benefits of combining open data and AI for the public good. Therefore, the project will achieve global impact by strengthening the open fiscal data international agenda.

I am convinced that, as the project develops, other potential users and partners will emerge. For instance, the UK government has dedicated teams in DFID and ONS to achieve the 2030 agenda. I am sure that they will be interested in adopting the project's tools. Likewise, international donors could assess how coherent are the conditions that they impose on the recipient countries on how to spend international aid. Overall, the project has enormous impact potential. Thus, should I be awarded the ESRC-Alan Turing Institute Fellowship, I am confident that I will be able to materialise it.