{"slug":"first-american-data-analytics-fine-tunes-open-source-llms-on-databricks-cutting-extraction-costs-70","url":"https://findausecase.com/use-cases/first-american-data-analytics-fine-tunes-open-source-llms-on-databricks-cutting-extraction-costs-70","title":"First American Data & Analytics fine-tunes open-source LLMs on Databricks, cutting extraction costs 70%","description":"First American Data & Analytics (DNA), a property-centric information provider to the real estate and title insurance industries, used the Databricks Data + AI Platform to fine-tune open-source LLMs (Mistral, Llama 3, Llama 3.1) for page-level classification and extraction of 100+ data fields from roughly 4 million historical title policy images dating to the 1930s. Using Delta Lake, Databricks Model Training, Managed MLflow, and serverless Model Serving on about 50 GPUs, the team fine-tuned models in two weeks versus the two-plus months it previously took on other platforms. The project cut extraction costs by 70%, reduced project completion time by 75% (months to weeks), and increased the number of data elements extracted tenfold.","company":"First American Data & Analytics","industry":"Real Estate","aiCapabilities":["Document Intelligence"],"technology":["Delta Lake","Unity Catalog","Mistral","Llama 3"],"deployment":"Public Cloud","problemStatement":"First American Data & Analytics maintains the industry's largest data repository of publicly recorded document images, over 8 billion unstructured documents, most stored with very limited metadata. The team received a set of roughly 4 million historical title policy images dating to the 1930s that needed page-level classification and extraction of more than 100 data elements per page, and earlier LLM approaches required huge training datasets and long fine-tuning times for these complex use cases.","solutionApproach":"Working with Databricks, First American DNA fine-tuned several open-source LLMs, including Mistral, Llama 3 and Llama 3.1, using Databricks Model Training on Delta Lake for data storage, Managed MLflow to streamline the LLM lifecycle, and roughly 50 GPUs for training; fine-tuned models were registered in Unity Catalog, and serverless Model Serving eliminated GPU-availability bottlenecks for deployment.","businessValue":"The fine-tuning approach cut extraction costs by 70% compared with a previous implementation, reduced data-extraction project time by 75% (from several months to weeks), and increased the number of data elements extracted tenfold; the fine-tuning step itself, which previously took over two months, was completed in two weeks.","evidence":{"band":"high"},"sourceUrl":"https://www.databricks.com/customers/fadna","dates":{"publishedAt":"2026-10-11T05:46:56.420Z","publishedAtSource":"pipeline","updatedAt":"2026-10-11T05:46:56.420Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/first-american-data-analytics-fine-tunes-open-source-llms-on-databricks-cutting-extraction-costs-70. Bulk republication requires permission."}