🎓 Graduate Student • Data Analytics & AI

Hi, I’m Dalton Payne.

I build data‑driven products that turn complex datasets into clear, actionable insight—using modern analytics, machine learning, and careful experimentation. Passionate about responsible AI, ML engineering, and credible causal inference.

Focus Areas

ML • NLP • CV

End‑to‑end pipelines

Toolbox

Python • SQL

PyTorch • Sklearn • DBT

Open to

Internships ’25–’26

Data/AI roles

Add your photo

Selected Projects

A few representative works spanning predictive modeling, NLP, computer vision, and data engineering. Filter to explore.

Time‑Series Predictive Maintenance

Predictive Maintenance with LSTMs

Built an end‑to‑end pipeline to forecast equipment failures using sensor telemetry (PyTorch, MLflow, Airflow). Included feature store, drift monitoring, and CI/CD to deploy to an API.

  • Improved early‑warning horizon while reducing alert fatigue (replace with your metric).
  • Automated retraining & model registry with MLflow; tracked lineage and reproducibility.
PyTorchMLflowAirflowTime Series
Domain‑Specific LLM RAG

Retrieval‑Augmented QA for Clinical Notes

Designed a privacy‑aware RAG system with dense retrieval and hybrid ranking; evaluated hallucinations with human‑in‑the‑loop labeling and prompt‑level guardrails.

  • Improved answer faithfulness and reduced unsupported claims (insert measured deltas).
  • Deployed on‑prem with vector DB; added anonymization and PHI redaction.
NLPRAGVector DBEvaluation
Vision Quality Inspection

Defect Detection with EfficientNet

Implemented transfer learning for visual inspection; combined weak supervision with focal loss to handle class imbalance; deployed as a lightweight on‑edge model.

  • Cut manual review time and stabilized precision/recall across lighting conditions.
Computer VisionEfficientNetONNXMLOps
Modern Analytics Stack

Analytics Engineering with dbt & BigQuery

Modeled event streams into clean, testable marts; added freshness tests and exposures. Built dashboards for product funnels and retention cohorts.

  • Reduced ad‑hoc SQL and sped up time‑to‑insight for product teams.
dbtBigQueryAirflowCohorts
Text Classification

Toxicity Classification with Robust Training

Built a multilingual classifier with adversarial training and data balancing to mitigate spurious correlations; emphasized transparent reporting.

TransformersHugging FaceBias & Fairness
Exploratory Analysis

Explaining Churn with SHAP

Mixed classical ML with explainability to surface drivers of churn; packaged a minimal “what‑if” interface for stakeholders to test scenarios.

XGBoostPandasSHAP

Technical Skills

Languages

PythonSQLRBash

ML / AI

PyTorchscikit‑learnTensorFlow TransformersNLPCV Time SeriesRecommenders

MLOps

MLflowWeights & BiasesDocker AirflowRayONNX

Data

PostgresBigQuerySnowflake Sparkdbt

Visualization

TableauPower BIPlotlyAltair

Methods

ExperimentationCausal InferenceBayesian A/B TestingOptimization

Experience

Data Science Intern · Acme Corp

Jun 2025 – Aug 2025 · Remote

  • Prototyped demand forecasting; partnered with Finance & Ops to align metrics and lift forecast accuracy (insert metric).
  • Productionized pipeline with feature store and CI checks.

Graduate Research Assistant · University Lab

Sep 2024 – Present

  • Investigating evaluation frameworks for retrieval‑augmented systems and prompt robustness.

Teaching Assistant · Intro to Machine Learning

Jan 2024 – May 2024

  • Led weekly labs; authored auto‑graded notebooks; mentored student projects.

Education

M.S. Data Analytics & Artificial Intelligence

Your University · 2024–2026

Coursework: Statistical Learning, Deep Learning, NLP, Data Engineering, Causal Inference, Cloud ML.

B.S. (Major)

Your University · 2020–2024

Honors / Activities: Data Science Club, Hackathons, Research Assistant.

Publications & Writing

  • Title — Venue/Blog, Year. Link
  • Title — Preprint, Year. Link

Certifications

  • Google Cloud Professional Data Engineer — Year
  • dbt Analytics Engineering — Year

Let’s connect

I’m open to internships and research collaborations in data/AI. The fastest way to reach me is email.

This opens your email client.