Bridging the gap between raw data chaos and actionable business strategy.
- Languages & Scripting: Python, R, SQL
- Data Engineering & Big Data: PySpark, Databricks, ETL Pipelines
- Machine Learning & AI: TensorFlow/Keras, LLM/RAG Evaluation, Scikit-Learn, Caret, Forecast (ARIMA)
- Analytics & Visualization: Tableau, Statistical Modeling, Cohort Segmentation
- Recycle or Compost (CV): Deep learning computer vision benchmarking custom CNNs vs. fine-tuned VGG19/InceptionV3 (91.6% test accuracy).
- Enterprise RAG & LLM Evaluation: Systematic evaluation study analyzing RAG failure modes and retrieval strategies across SEC filings.
- Workforce Attrition & Forecasting: Predictive turnover classification (C5.0), K-means clustering, and 24-month ARIMA time-series forecasting in R.
- App Store Sentiment & Topic Modeling: Distributed NLP pipeline using PySpark LDA topic modeling and logistic regression across 105K+ reviews.
📫 Connect with me: bridgetteheiner.com • LinkedIn