{"678591":{"#nid":"678591","#data":{"type":"news","title":"Competition Highlights Work of Georgia Tech Researcher Helping Drive Improvements in the Science of Conflict Forecasting ","body":[{"value":"\u003Cdiv\u003E\u003Cp\u003EIt\u2019s not every day a social science scholar gets a chance to shape a field from nearly the ground up, but that\u2019s the exciting reality in which David Muchlinski finds himself.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThe assistant professor in Georgia Tech\u2019s Sam Nunn School of International Affairs is one of only about 40 people worldwide working in the young field of conflict forecasting, with hopes of one day advancing models that could give governments, international organizations, NGOs, and others the kind of insight to help them head off conflict, not merely respond to it.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EIt\u2019s an exhilarating high-wire act for a young researcher living through a tumultuous period in world history.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u201cKnowing I could make a difference in some way in the world is cool to think about, but this is also a scientifically difficult and fascinating problem to crack,\u201d he said. \u201cYou\u2019re forced to put actual predictions out there and be judged by history about how right or wrong you are or were. Relatively few researchers in political science are willing to put their reputations or the validity of their models on the line in such a public way and be proven wrong, sometimes very wrong.\u201d\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EConflict Competition Seeks to Drive Innovation\u003C\/strong\u003E\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThat\u2019s exactly what he\u2019s doing now as part of a triennial academic competition to drive improvements in the science of conflict forecasting.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/inta.gatech.edu\/people\/person\/david-muchlinski\u0022 rel=\u0022noreferrer noopener\u0022 target=\u0022_blank\u0022\u003EMuchlinski\u003C\/a\u003E and Ph.D. student Chandler Thornhill\u2019s \u003Ca href=\u0022https:\/\/viewsforecasting.org\/wp-content\/uploads\/Muchlinski_VIEWSPredictionChallenge2023.pdf\u0022 rel=\u0022noreferrer noopener\u0022 target=\u0022_blank\u0022\u003Econtribution\u003C\/a\u003E to the triennial \u003Ca href=\u0022https:\/\/viewsforecasting.org\/\u0022 rel=\u0022noreferrer noopener\u0022 target=\u0022_blank\u0022\u003EViolence and Early Warning System\u003C\/a\u003E (VIEWS) Prediction Challenge involves a new two-step model that the researchers hope better addresses common challenges in violence prediction and outperforms existing models.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u0022One of the primary challenges in conflict forecasting is that, fortunately, there are relatively few cases that researchers are able to study,\u201d Thornhill said. \u201cIf we are looking at all states across multiple years, the number of states experiencing a conflict in a given year is relatively small, meaning a lot of zeroes in the data. This is where the importance of a two-step model comes in.\u201d\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThe first step in their model evaluates whether a given country is likely to experience conflict. The second step estimates the level of intensity of conflicts in countries where it is predicted to occur.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EMuchlinski and Thornhill say their model predicts Ethiopia, Ukraine, Yemen, Afghanistan, and Israel will lead the world in armed conflict fatalities during the competition, which runs through May.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EHistory of Conflict Prediction\u003C\/strong\u003E\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThe field dates back to the 1980s, with scholars such as Bruce Bueno de Mesquita of New York University and Philip Schrodt, a senior research scientist at Parus Analytics and former professor at Penn State and the University of Kansas.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u201cThey led early efforts to collect numerical data on conflicts and wars, systematize this data into relational databases, and use computer and\/or statistical modeling to predict future conflicts,\u201d Muchlinski said. \u201cThese early efforts were often sponsored by agencies like the CIA, and much of the early models were proprietary and not subject to public scrutiny.\u201d\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThe current field began to emerge only in the 2010s as scholars, including Muchlinski, began using machine learning techniques to advance their predictive capabilities. It was during this time that Muchlinski published his first paper on the topic, \u201c\u003Ca href=\u0022https:\/\/doi.org\/doi:10.1093\/pan\/mpv024\u0022 rel=\u0022noreferrer noopener\u0022 target=\u0022_blank\u0022\u003EComparing Random Forest with Logistic Regression for Predicting Class-Imbalanced Civil War Onset Data\u003C\/a\u003E\u201d in 2016, in \u003Cem\u003EPolitical Analysis\u003C\/em\u003E.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EMachine learning techniques and large language models (LLMs) that power AI chatbots such as ChatGPT are rapidly taking hold in the field, promising greater predictive capabilities, Muchlinski said. But many challenges remain.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u201cWars are complex processes,\u201d he said. \u201cWhile we theorize that some factors may be important, like weak states generally don\u2019t attack stronger states, or that states declining in power may launch preemptive wars before they become too weak, these explanations generally explain only a handful of cases, or are so commonsensical and outside the realm of good scientific theory as to be meaningless.\u201d\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u201cWe don\u2019t know many things that may cause conflict, and we don\u2019t know where to look for answers,\u201d he said. \u201cAnd even worse, we don\u2019t know if explanations for one conflict explain others, or if each conflict is more or less unique and explained by idiosyncratic factors.\u201d\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u003Cstrong\u003EWhat\u2019s Next for the Field?\u003C\/strong\u003E\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EMuchlinski said conflict prevention scholars are driven not only by the challenge but also the possibility of someday arming governments and others with the information and time they need to try to stave off conflicts instead of simply responding to them.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u201cThe ultimate goal of our work is being able to effectively forecast with at least a year\u2019s notice that something unforeseen like the current Israel\/Hamas or the Russia\/Ukraine war will occur,\u201d Muchlinski said.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EThe use of LLMs shows good promise in helping researchers better understand problems like these, Muchlinski said. But the field also needs more strenuous theory development and testing, which competitions like the one Muchlinski and Thornhill are working on may help drive.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003EBut even if they get it right and learn to make accurate, timely predictions, it\u2019s still going to be on world leaders to solve problems before they get out of hand, Muchlinski noted. Data science can\u2019t solve that problem, he said.\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E\u003Cdiv\u003E\u003Cp\u003E\u201cNo statistical model will convince reluctant politicians to loosen the purse strings. Ultimately that\u2019s where the difference would lie, at the intersection of forecasting and political will\u201d he said. \u201cOne of those is a much easier problem to solve than the other.\u201d\u0026nbsp;\u003C\/p\u003E\u003C\/div\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EIvan Allen College of Liberal Arts researchers David Muchlinski and Chandler Thornhill are part of a small community of researchers worldwide trying to advance the science of conflict prediction.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Ivan Allen College of Liberal Arts researchers David Muchlinski and Chandler Thornhill are part of a small community of researchers worldwide trying to advance the science of conflict prediction."}],"uid":"34600","created_gmt":"2024-11-21 18:07:26","changed_gmt":"2024-12-10 16:06:03","author":"mpearson34","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2024-11-21T00:00:00-05:00","iso_date":"2024-11-21T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"675710":{"id":"675710","type":"image","title":"muchlinski thornhill.jpg","body":"\u003Cp\u003EAssistant Professor David Muchlinski, left, and Ph.D. student Chandler Thornhill, both of the Sam Nunn School of International Affairs, are among only 40 or so researchers worldwide involved in conflict prediction, using statistical and other methods to predict violent outbreaks.\u003C\/p\u003E","created":"1732212655","gmt_created":"2024-11-21 18:10:55","changed":"1732212655","gmt_changed":"2024-11-21 18:10:55","alt":"David Muchlinski and Chandler Thornhill sit facing the camera in front of a yellow wall with a portrait of former Sen. Sam Nunn.","file":{"fid":"259366","name":"muchlinski thornhill.jpg","image_path":"\/sites\/default\/files\/2024\/11\/21\/muchlinski%20thornhill.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2024\/11\/21\/muchlinski%20thornhill.jpg","mime":"image\/jpeg","size":1313160,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2024\/11\/21\/muchlinski%20thornhill.jpg?itok=07NcRT06"}}},"media_ids":["675710"],"related_links":[{"url":"https:\/\/iac.gatech.edu\/news\/item\/638907\/georgia-tech-researcher-uses-machine-learning-search-ways-predict-political","title":"Georgia Tech Researcher Uses Machine Learning in Search for Ways to Predict Political Violence"}],"groups":[{"id":"1281","name":"Ivan Allen College of Liberal Arts"},{"id":"1285","name":"Sam Nunn School of International Affairs"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[{"id":"71901","name":"Society and Culture"}],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003E\u003Ca href=\u0022mailto:michael.pearson@iac.gatech.edu\u0022\u003EMichael Pearson\u003C\/a\u003E\u003Cbr\u003EIvan Allen College of Liberal Arts\u003C\/p\u003E","format":"limited_html"}],"email":["michael.pearson@iac.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}