Big Data

Moneyball Diplomacy

A citizen suffering from a head wound after deadly ethnic and religious rioting, in Jos, Nigeria in 2008.

A citizen suffering from a head wound after deadly ethnic and religious rioting, in Jos, Nigeria in 2008. // Sunday Alamba/AP File Photo

When violence spiked in Nigeria’s conflict-ridden Delta region in 2008, the government launched an amnesty program, offering to protect militants from prosecution and pay for their arms if they’d lay them down.

It seemed like a reasonable approach and one that might work.

But when the U.S. State Department’s Bureau of Conflict and Stabilization Operations started mining data from public news reports about the conflict, they discovered something interesting. The amnesty program did reduce conflict but the effect was only short term, Amir Bagherpour, a senior adviser in the bureau, said. After a while the level of violence in the Delta returned to its upward trend.

Bagherpour’s bureau also used its historical data to simulate how the various groups in the Delta might act, based on different scenarios, going forward. The system considered more than one vigintillion (that’s 10 to the 63rd power) combinations of unique interactions between the groups, Bagherpour said, and produced expected outcomes for the combinations it deemed most likely.

“This allowed us to anticipate the potential evolution of how things may change over time in regard to militancy and the impact that random events could have on the outcome of militancy in the future,” he said.

Bagherpour was speaking at a State Department event called “Moneyball Diplomacy” focused on how new data analysis tools may help the U.S. better understand the world and achieve foreign policy goals.

This in-depth analysis can’t tell the U.S. or the Nigerian governments precisely how to fix conflict in the Delta, he said, but it can help “clear the fog” so qualitative analysis can be more effective.

New tools have emerged during the past decade capable of crunching through large troves of “big data” and spotting patterns that were never apparent before. Big data refers to large amounts of unstructured data such as satellite information, sensor feeds, text documents and anything else that doesn't neatly fit into a spreadsheet.

Kenneth Cukier, data editor for the Economist magazine, described big data during Friday’s event as “a new raw material, a vital resource and the oil of the information economy.”

Data analysis could help the State Department shift the way it manages overseas aid, election monitoring and other issues from a primarily qualitative to a primarily quantitative approach, he said.

This article has been updated to clarify the number of possible interactions between groups in the Niger Delta a State Department system examined.

Threatwatch Alert

Thousands of cyber attacks occur each day

See the latest threats

JOIN THE DISCUSSION

Close [ x ] More from Nextgov
// September 29
X CLOSE Don't show again

Like us on Facebook