I am building a research-oriented GitHub portfolio in preparation for a PhD in Applied Economics, with a focus on causal inference and empirical analysis of technology and AI-related institutional change.

My background is in Fintech product management, where I worked on system-level design, data workflows, and decision-making processes. This repository documents my transition toward empirical research through independent replication, methodological learning, and applied coding work.

The projects here are designed to be reproducible and transparent, emphasizing empirical strategy, identification, and implementation rather than production-level engineering.

My current research centers on empirical questions at the intersection of technology, organizations, and economic outcomes, including:

• Applied microeconomics of technology and AI
• Causal inference using panel data and quasi-experimental designs
• Economic and organizational impacts of AI-driven decision systems
• Technology adoption and institutional responses in firms and markets

AI systems (e.g., Agentic AI) are treated as economic or institutional shocks rather than as engineering objects.

I primarily work with applied econometric and empirical research tools, including:

• Difference-in-Differences (DiD)
• Event-study designs
• Fixed effects and panel data methods
• Replication and robustness analysis

• Programming: Python (pandas, statsmodels, linearmodels)
• Research workflow: data cleaning, replication, version control (Git/GitHub)
• Reproducibility: structured repositories, documented assumptions, executable code

• Replicating applied econometrics papers on technology, regulation, and institutional change
• Designing DiD and event-study frameworks where AI adoption is modeled as an exogenous or quasi-exogenous shock
• Developing a reproducible research portfolio suitable for PhD-level evaluation

This GitHub profile documents my learning process through implementation and replication.
The emphasis is on empirical reasoning, identification strategies, and independent problem-solving rather than AI system engineering.