Skip to content
View dustintdn's full-sized avatar

Block or report dustintdn

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dustintdn/README.md

Hi, I'm Dustin 👋

Senior Data Scientist @ Aon | Quantitative Methods in the Social Sciences M.A., Columbia University

Welcome to my playground for exploring new project ideas and experiments! I primarily work at the intersection of people analytics, applied ML, and causal inference - using data to answer questions about human behavior at scale. Currently building tools that bring LLMs into real-world workflows during the day, and designing movement-based creative code at night.

Featured Projects 🚀

Project Description
ai-citation-audit CLI tool measuring brand visibility across LLM-powered apps (ChatGPT, Claude, Perplexity)
churn-nba Small & medium-sized business (SMB) churn prediction (XGBoost, SHAP) + next-best-action for customer retention
geo-incrementality-experiment Causal geo-experiment measuring incremental lift (CausalImpact)
mmm-budget-optimization Marketing Mix Model (MMM) to optimize budget allocation for paid media
llm-engagement-summarizer LLM-powered theme extraction from employee engagement surveys
ai-resolution-quality Causal inference (PSM + DiD) on AI-assisted customer support outcomes
lm-eval-demo Benchmarking SLMs on structured extraction, RAG Q&A, intent classification, and latency
voice-of-customer-analytics E2E NLP pipeline for customer complaint insights (BERTopic clustering, LLM extraction)

Pinned Loading

  1. ai-citation-audit ai-citation-audit Public

    CLI tool for auditing brand visibility across LLMs - queries ChatGPT, Claude, and Perplexity with structured prompt batteries and outputs citation rate, position, and sentiment by competitor

    Python

  2. churn-nba churn-nba Public

    Churn prediction + next-best-action engine for SMB retention - XGBoost model with SHAP explanations, served via FastAPI and Streamlit

    Jupyter Notebook

  3. mmm-budget-optimization mmm-budget-optimization Public

    Marketing Mix Model that quantifies channel contribution and optimizes budget allocation across paid media using PyMC.

    Jupyter Notebook

  4. llm-engagement-summarizer llm-engagement-summarizer Public

    Analyzing employee engagement survey comments using LLM-powered topic/theme summarization

    Python

  5. geo-incrementality-experiment geo-incrementality-experiment Public

    Causal geo-experiment measuring incremental campaign lift with Bayesian structural time series (CausalImpact)

    Jupyter Notebook

  6. lm-eval-demo lm-eval-demo Public

    Benchmarking SLMs on structured extraction, RAG Q&A, intent classification, and latency

    Jupyter Notebook