About me

I am a Fulbright scholar with over eight years of experience specializing in complex data problem management. During my tenure as a research and teaching assistant at the University of Illinois at Urbana Champaign, I successfully contributed to various projects involving the development and validation of models. Specifically, I focused on creating and implementing innovative algorithms to predict market trends. Additionally, I worked extensively on designing loss forecasting and stress testing models for credit cards and unsecured lending. My dissertation revolved around the application of Bayesian Deep Learning to model key metrics such as Probability of Default (PD), Loss Given Default (LGD), and Exposure at Default (EAD). As a seasoned data scientist, I have conducted comprehensive statistical analyses and developed predictive models for complex datasets, utilizing Python and R. My skillset extends to designing and executing A/B testing methodologies to optimize marketing strategies. Collaborating closely with fellow data scientists, engineers, and business stakeholders, I have consistently delivered data-driven solutions to address intricate business challenges. I possess in-depth knowledge of regulatory frameworks such as Basel I, II, and III, the Dodd-Frank Act Stress Test (DFAT), and the Comprehensive Capital Analysis and Review (CCAR), set forth by the Federal Reserve Systems. My areas of expertise encompass Machine Learning, Deep Learning, Reinforcement Learning, Econometrics, Predictive Modeling, and Financial Risk Management. Additionally, I am proficient in SAS, R, Python, STAT, Java Script, Latex, and GIS, enabling me to navigate diverse technological landscapes to extract valuable insights from data. Some of my apps can be found here