作品集 · Selected work

Projects in bloom

A selection of projects spanning data analytics, machine learning and applied AI. Each one turns raw data into clear, actionable decisions.

代理↗

AI Data & Workflow Agent

Multi-agent AI assistant built with LangGraph and Gemini that routes plain-English requests to specialized SQL and ETL agents. The SQL agent writes a query, has a second model review it for safety, then runs it on PostgreSQL and returns checked results. The ETL agent pulls data from APIs and transforms it with pandas, saving to CSV, JSON or Parquet.

  • Python
  • LangGraph
  • Gemini API
  • SQL
  • PostgreSQL
  • pandas
  • Multi-Agent Systems
調査

AI Research & Due Diligence Agent

Multi-agent AI workflow that automates research, analysis and the writing of source-grounded business reports. Uses the OpenAI and Tavily APIs to gather outside information and combine findings with traceable citations. A human-in-the-loop review step checks the research direction before parallel analyst agents run the multi-step analysis.

  • Python
  • LangGraph
  • LangChain
  • OpenAI API
  • Tavily
  • Human-in-the-Loop
購買↗

E-Commerce Funnel & Retention Analysis

Traced 300,000 user events through a multi-category store to explain why 88,000 monthly users and $1.68M in revenue converted under 5%. SQL analysis put the break at discovery rather than checkout. 93.2% of sessions never added to cart. Month-1 retention sat at 1.2% against an 8 to 15% benchmark and smartphones were the largest recoverable category. Delivered as a three-page Power BI report with cohort retention and RFM segmentation.

  • SQL
  • MySQL
  • Power BI
  • Python
  • Cohort & Retention Analysis
  • Funnel Analytics
不正

Medicare Provider Risk Analytics

End-to-end risk analytics pipeline built on CMS Medicare data across about 1.67M providers to spot anomalous billing behavior. Engineered peer-relative features and trained XGBoost models to rank providers by potential risk so investigators can focus on the right cases. SHAP explainability turns each prediction into plain risk drivers that non-technical decision-makers can act on.

  • Python
  • XGBoost
  • SHAP
  • Feature Engineering
  • Explainable AI
  • Healthcare Analytics
交通↗

NYC Congestion Pricing Causal Impact

Measured the real effect of NYC congestion pricing on 65M taxi trips with a difference-in-differences design. The naive before and after read says traffic inside the zone rose 13.2%. Controlling for citywide demand growth flips the sign. Trips fell 17.5% at p below 0.001 and speeds rose 6.5%. That is roughly 75,000 fewer trips a week. Validated with parallel-trends testing, a placebo toll date and robustness windows.

  • Python
  • statsmodels
  • Causal Inference
  • Difference-in-Differences
  • A/B Testing Methods
  • Policy Analytics
顧客↗

Customer Segmentation with RFM Analysis

Segmented 3,490 retail customers into 11 behavioural groups so a bike parts business could target the right 1,000 prospects. Cleaned four raw tables covering 20,000 transactions then scored every customer on recency, frequency and profit. Those quartile-ranked scores drive the segment map across $21.9M in sales and $10.8M in profit. Platinum Customers came out at just 4.8% of the base while buying 70% more often than average.

  • Python
  • pandas
  • RFM Segmentation
  • Tableau
  • Customer Analytics
  • Data Cleaning
公正↗

Algorithmic Fairness Audit (COMPAS)

Rebuilt the ProPublica and Northpointe dispute over the COMPAS recidivism score from raw data and showed both sides were right. Black defendants who never reoffended were flagged high risk 44.8% of the time against 23.5% for white defendants. The score still stayed calibrated for both groups. Proved the gap is forced by differing base rates and holds across 800 combinations of PPV and FNR. Equal precision and equal false positive rates cannot both be satisfied.

  • Python
  • pandas
  • Responsible AI
  • Model Fairness & Bias Auditing
  • Classification Metrics
  • Statistics