Projects by Dan Baker

UFC Fight Predictor (ML)

Machine learning model (Random Forest) trained on historical UFC stats. Predicts fight winners via a Flask API deployed on Render.

Python, scikit‑learn, Flask, Render

Real-time Crypto Pipeline

Ingested live Bitcoin data via WebSocket, processed with Kafka & Spark Streaming, stored in S3.

Python, Kafka, Spark, AWS

Batch ETL: E‑commerce Sales

Airflow DAG extracting from PostgreSQL, transforming with dbt, loading into Redshift.

Airflow, dbt, Redshift, SQL

Data Lake on AWS

Built a serverless data lake with Glue crawlers, Athena queries, and Terraform.

AWS Glue, Athena, Terraform