Research
Statistical research in network models, causal inference, and simulation-based methods.
Research Interests
- Statistical modeling for dynamic and network-structured data
- Causal inference, experimental design, and geo-experimentation
- Simulation-based inference and Monte Carlo methods
- High-dimensional data analysis and reproducible statistical workflows
Publications & Manuscripts
Attractor-Based Coevolving Dot Product Random Graph Model
Modeled polarization and flocking behavior in dynamic networks using graph embedding methods. Proposed an attractor-based framework for coevolving latent-space network dynamics.
- random dot product graphs
- spectral embedding
- simulation
- latent-space models
Simplex-Constrained Orthogonal Transformation Estimation
Introduced a penalty function to align point clouds with the simplex under orthogonal constraints. Targets applications in latent-space model identifiability and estimation.
- optimization
- orthogonal constraints
- point cloud alignment
- estimation theory
Awards & Recognition
2nd Place — NESS Statathon 2023: Predictive modeling for car insurance risk
4th Place — NESS Statathon 2024: Customer conversion prediction pipeline for marketing optimization
2nd Place — NESS Statathon 2025: Predictive modeling for car insurance risk