A1411
Title: Source inference for complex forensic evidence using a contrastive learning framework
Authors: Danica Ommen - Iowa State University (United States) [presenting]
Samuel Fox - Iowa State University (United States)
Christopher Saunders - South Dakota State Univerisity (United States)
JoAnn Buscaglia - FBI Laboratory (United States)
Abstract: To interpret the value of forensic evidence resulting from paired item data, the common source identification framework asks: Do the items share a common unknown source, or do they come from two different unknown sources? This question can be addressed using a variety of forensic statistics techniques, including the usual two-stage, likelihood ratio, and Bayes factor approaches. Contrastive learning methods address the question using two major components: a method for quantifying the similarity (or dissimilarity) of pairs of evidence items, and a method for determining the best separation of within-source or between-source comparisons. Contrastive learning methods are particularly useful when the data derived from the evidence is high-dimensional or complex. In this case, the contrastive learning algorithms take advantage of high-performing artificial intelligence and machine learning tools to avoid specifying complicated probability models for the usual forensic statistics approaches. A contrastive learning algorithm framework is developed for complex evidence. The output of the contrastive learning algorithm can be used in a score-based likelihood ratio to interpret the value of evidence. Additional work is necessary to apply the method to the specific source question (whether an item came from a specific known source).
