← Back to Event List

Machine Learning Seminar[In-Person]: Dr. Ansu Chatterjee

University of Maryland, Baltimore County


Mathematics/Psychology : 412

Date & Time

April 26, 2024, 2:00 pm3:00 pm


Talk title: Explainable ML for imbalanced spatio-temporal data: a study on political violence

Abstract: Domestic crime, conflict, and instability pose a significant threat to many contemporary governments. These challenges have proven to be particularly acute within modern-day Mexico. Machine learning, especially deep learning, has been proven to be highly effective in predicting future conflicts using word embeddings in Convolutional Neural Networks (CNN) but lacks the spatial structure and, due to the black box nature, cannot explain the importance of predictors. We develop a novel methodology using machine learning that can reasonably accurately classify future anti-government violence in Mexico. We further demonstrate that our approach can identify important leading predictors of such violence. Using a variety of political event aggregations from the ICEWS database alongside other textual and demographic features, we trained various classical machine learning algorithms, including but not limited to Logistic Regression, Random Forest, XGBoost, and a Voting classifier.