Data Science & Mathematics @ NYU
Interactive AI systems for agent workflows, biomedical reasoning, NBA roster intelligence, and predictive modeling — built as product-grade dashboards backed by original project code and artifacts.
Featured systems
4
agent, reasoning, prediction, POI
Backend
FastAPI
wraps original project code
Demo data
mixed
artifacts plus POI mock evidence
system overview
An LLM-driven NBA player recommendation and scouting workflow built around team need diagnosis, player strength vectors, fit ranking, robustness checks, and grounded Q&A.
An agentic biomedical QA system that answers medical reasoning problems through planning, evidence retrieval, Tool Facts, verification, and final answer synthesis.
A neural-network and machine-learning prediction system that estimates annual insurance costs using original saved model artifacts, uncertainty signals, and feature drivers.
A small LLM-agent style workflow for POI data quality judgment using mock map, merchant, user feedback, and spatial evidence.
featured work
Each project calls a FastAPI wrapper that either recomputes with the original code path or exposes provenance-backed original artifacts when live dependencies are unavailable.
AI Agent System
An LLM-driven NBA player recommendation and scouting workflow built around team need diagnosis, player strength vectors, fit ranking, robustness checks, and grounded Q&A.
Pipeline nodes
11
WebApp registry
Eval metrics
7
zero-shot vs tools
Backend
FastAPI
imports nba_agent
Reasoning System
An agentic biomedical QA system that answers medical reasoning problems through planning, evidence retrieval, Tool Facts, verification, and final answer synthesis.
Published acc.
0.69564
fine-tuned GPT-4.1 + tools
Passes
2
plan then answer/verify
Tool families
6
FDA, DailyMed, RxNav, more
Predictive Model
A neural-network and machine-learning prediction system that estimates annual insurance costs using original saved model artifacts, uncertainty signals, and feature drivers.
Inputs
6
age, BMI, children, sex, region, smoker
Best model R2
0.846
XGBoost comparison metric
Backend
FastAPI
wraps original shared.py
LLM Agent / Map Data Quality
A small LLM-agent style workflow for POI data quality judgment using mock map, merchant, user feedback, and spatial evidence.
Evidence chunks
10+
mock multi-source signals
Top-K retrieval
5
ranked evidence
Workflow steps
7
visible tool trace
build principles
planner
Converts the natural-language roster request into team, goal, top-k, recent-game window, and availability filters.
planner
Selects visible workflow sections, validates dependencies, records skipped tools, rationales, and fallback state.
analytics
Uses recent team statistics and league z-scores to compute a need-weight vector.