Daniel P. Findley

• Prototyped, developed, maintained and enhanced an Active Listening AI system that transcribes, summarizes and extracts facts from client meetings and grew to more than 70,000 monthly uses.
• Evaluated transcription, generation and diarization models; led a transcription model change that saves approximately $1.4 million annually.
• Developed and maintained agentic fact extraction technology that converts large volumes of unstructured text into actionable insights.
• Developed a planning-page content recommendation system using state-of-the-art deep learning techniques, CatBoost and document embeddings.
• Contributed to an agentic coding harness that improves team productivity.

• Productionalized a content-based recommendation system to improve financial plans using CatBoost, document embeddings and word embeddings.
• Used the recommendation system to evaluate financial plans holistically and measure their impact on sales.
• Developed an automated plan-generation model using a recurrent neural network to improve financial advisor efficiency and plan quality.
• Performed analytical engineering work for key stakeholders.

• Developed page-classification models using traditional machine learning and natural language processing.
• Designed entity relationship and data flow diagrams for data intake pipelines and migrations from legacy systems to a unified data platform.
• Created ETL pipelines for downstream consumption.

• Used census data in R and Datawrapper to visualize and explain factors behind the digital divide across Wisconsin.

GPA: 4.00 / 4.00

GPA: 3.92 / 4.00 · Summa Cum Laude · Core Honors Program

GPA: 4.09 / 4.00

• Built full end-to-end data pipeline with automated scraping from multiple football data sources, data manipulation, and quality control.
• Outputs goal, assist, clean sheet and match score predictions using XGBoost models and Monte Carlo match simulations.