Small Data, AI and ML - Predicting Coup d'état

Can AI / ML spot countries at risk of a sudden change in leadership in a coup attempt?

Looks like so. Researchers at the University of Central Florida are working with a system called CoupCast to estimate the likelihood that an individual country will undergo a coup d’état.

CoupCast?predicts?the probability that a coup will overthrow each of the world’s national leaders in each month.

The team gathered a proprietary training dataset by deducing likely drivers of coup attempts from academic research on coups dating back to 1920. In addition, it collected data detailing contemporaneous economic conditions such as gross domestic products, social conditions such as infant mortality, political conditions such as election schedules and regime longevity, and leader profiles such as age and military background. The team trained two architectures, a random forest and an ensemble of regression models, to predict coup probabilities in logarithmic space, allowing a finer assessment of risk where coups are rare. They trained the regression models in an autoregressive fashion: First they trained a model on data between 1950 and 1974 to predict coup risks for 1975. They added the 1975 predictions to the dataset and retrained the model to predict risks for 1976, and so on to the present.?The two models are similarly good at predicting coups, but they're much more accurate when combined. The team combines their outputs using a?generalized additive model.

CoupCast’s dataset included only 600 positive examples.

And YES in 2021, the system predicted upheavals in Chad and Mali.

A military offensive in Northern?Chad, initiated by the?Chadian?rebel group Front for Change and Concord in?Chad?(FACT), took place from 11 April to 9 May?2021.

The 2021 Malian coup d'état began on the night of 24 May 2021 when the Malian Army led by Vice President Assimi Go?ta captured President Bah N'daw, Prime Minister Moctar Ouane and Minister of Defence Souleymane Doucouré.

Technology that helps people see what’s on the horizon may help prevent coups from spiraling into civil wars and humanitarian crises or at least help people prepare for the worst. Modeling political unrest is an important but challenging small-data problem; CoupCast’s dataset included only 600 positive examples.

Given the extremely high stakes of international relations, a data-driven approach seems like a productive complement to human analysis.

References:

COUPCAST: METHODOLOGY

Dataset in Github

Computational Social Science and Political Event Analysis