Omid Askarisichani successfully defended his PhD on the topic of "Explainable Models of Performance on Networks", he will join Google as a Machine Learning Software Engineer.

Committee: Ambuj Singh (Chair), Francesco Bullo, Noah E. Friedkin, Xifeng Yan

Abstract: Networks model complex systems in myriad applications, including social media, finance, and political systems. In such settings, nodes often represent people, artificial agents, or political parties while edges portray their positive or negative relationships. Interpersonal relationships change due to a person’s cognitive biases, societal roles, and what their in-group perceptions are. These relationships impact one's task performance. Often times, there is a need to estimate the underlying relationships and forecast their changes. This dissertation is at the intersection of machine learning, network science, and social science. In our studies, we use graph theory, natural language processing, and convex optimization to extract information on how to improve the performance of individuals in financial and social systems.

By leveraging data, we study how the patterns of influence and relationships may impact the performance of stock traders. We build upon theories from sociology, namely structural balance theory—which describes the dynamics that govern the sentiment of interpersonal relationships—and assess the impact on stock traders' profitability. Furthermore, we show a generalization of structural balance theory that describes the dynamics of relationships among countries over more than two decades. We capture their dynamics using a time-varying Markov model, pinpoint the international shocks, and international conflicts. Finally, we find the factors leading to an individual becoming influential in the underlying social system and efficiently estimate an individual's influence on others on the basis of their expertise, communication contents, and social confidence. Our experimental results demonstrate that the proposed neural network model surpasses baseline algorithms.