Kun W. Email & Phone Number

New York, New York, Us

Model Risk: Model Validation for Market Risk & Credit Risk Expected Shortfall / Value at Risk Basel IMA / FRTB

New York, New York, Us

Credit Risk: Credit Risk Modeling for Credit Card, Personal Loan, Small Business Loan, Mortgage, Warehouse Lending, etc. PD / LGD / EAD / Loss Forecasting CECL / CCAR / Basel AIRB

San Francisco, California, Us

Compliance Risk:Fair Lending Modeling / Causal Inference: Home Equity, Home Mortgage, Auto Loan, etc.Disparity Impact Monitoring / AB test / Treatment effect

Fort Collins, Co, Us

Applied and Computational Math: Data Analysis, Machine Learning, Predictive Modeling, Dimensionality Reduction, Optimization, and Simulation.Video Analysis: Develop a manifold based algorithm for detecting anomalies in video sequences by Multivariate State Estimation Technique. Exploit the geometry of Grassmann manifolds and their rich collection of orthogonally invariant metrics.Image Analysis: Develop object recognition algorithms for adapting the classifier trained on a source domain to recognize instances from a new target domain. Images collected from three domains: Amazon, DSLR camera, and webcam are studied.Genomic Analysis: Develop algorithm to identify genes that provide deeper insight into complex interactions while remaining directly connected to diagnostic utility. Demonstrate that the selected genes expose relevant pathways that other approaches would have missed.Clinical Analysis: Employ Canonical Correlation Analysis (CCA), Support Vector Machine(SVM), and Random Forests (RF) classifiers to select the optimal subspace of biomarkers from alarge hematological data set collected from infants with suspected sepsis. Address the identification of optimal biomarkers for the rapid diagnosis of neonatal sepsis.Infectious Disease Modeling: Building mathematical models based on Ebola time series microarray data. Developing Early Warning Algorithms for predicting Ebola infection outcomes by Anomaly Detection techniques.

New Haven, Ct, Us

Control of Dynamical Systems and Outcome Prediction in Mathematical Modeling: Investigate several systems of ordinary differential equations (ODEs) that model the host immune response to a pathogen load. Implement patient-to-patient variability in the ODE models. Use logistic regression with one-versus-all classification to predict the discrete steady-state outcomes of the system.

Bachelor Of Science (Bs), Physics

Doctor Of Philosophy (Ph.D.), Theoretical And Mathematical Physics