{"id":3912,"date":"2023-11-13T08:51:34","date_gmt":"2023-11-13T08:51:34","guid":{"rendered":"https:\/\/beta74.thewebsitepreview.com\/wavicle\/dev\/?p=3912"},"modified":"2025-11-18T07:49:10","modified_gmt":"2025-11-18T07:49:10","slug":"healthcare-product-supplier-launches-feature-store","status":"publish","type":"post","link":"https:\/\/beta74.thewebsitepreview.com\/wavicle\/dev\/case-studies\/healthcare-product-supplier-launches-feature-store\/","title":{"rendered":"Healthcare Product Supplier Launches Feature Store for Improved Data Science Workflow"},"content":{"rendered":"

This company, an industry-leading supplier of products, platforms, and services for the healthcare industry, came to Wavicle to improve data access and streamline data science workflows in\u00a0<\/span>Databricks<\/span><\/a>.<\/span>\u00a0<\/span><\/p>\n

Wavicle brought development-ready data into Databricks through ingestion work and developed a process to ensure consistent feature calculations, nomenclature, and availability for models in different parts of the business: a feature store. The feature store reduces the time spent on preprocessing, feature engineering, and data blending and allows models to easily convert from development to production.<\/span>\u00a0<\/span><\/p>\n

Wavicle taught this healthcare product supplier about the feature store, implemented a minimum viable product (MVP) in Databricks, and provided a framework for further feature store usage in Databricks.<\/span>\u00a0<\/span><\/p>\n

Challenges accessing clean, defined data and high time-to-model data turnover rate<\/span>\u00a0<\/span><\/h2>\n

When building models, data scientists on the healthcare product supplier\u2019s team did not always know where data was located or who the relevant data experts were. Data that had been used in one data science project might be required for a new project, but data scientists were hesitant to use the cleaned data because they lacked visibility to how the data had been sourced and cleaned. Data definitions were not always well documented, and models suffered delays moving from experimentation to production because the underlying data sources were not production ready.<\/span><\/p>\n

This created rework for data engineers, discouraged experimentation with new data sources within the data science team, and delayed model deployment. The team needed a better way of understanding and accessing their data that could supply clean, defined data for data science projects and streamline workflows moving forward.<\/span>\u00a0<\/span><\/p>\n

Solving data challenges with a robust feature store<\/span>\u00a0<\/span><\/h2>\n

Wavicle\u2019s data and analytics experts helped the healthcare supply company improve their data science workflows through a multi-step process to implement a feature store.<\/span>\u00a0<\/span><\/p>\n

Research and education<\/span>\u00a0<\/span><\/h3>\n

The healthcare product supplier had originally engaged Wavicle to bring the data underlying its\u00a0<\/span>machine learning models<\/span><\/a>\u00a0into Databricks. The Wavicle team was aware of the feature store capabilities in Databricks \u2013 powered by the Unity Catalog \u2013 and consequently identified that the feature store could address many of the company\u2019s challenges.<\/span><\/p>\n

Wavicle created an overview of the feature store benefits and an architecture diagram that served as a guidepost throughout the project. The customer\u2019s team used this information to assess the importance of the feature store and decided to prioritize a feature store MVP along with the Databricks ingestion work.<\/span><\/p>\n

\"Architecture\u00a0<\/span>Pilot implementation<\/span>\u00a0<\/span><\/h3>\n

Pipelines had been identified for ingestion to the silver layer in Databricks for the highest priority models. Although these data pipelines had business definitions associated with them, the data did not yet meet the high standard of a feature store, which allows for consistent use of features across domains and for models that were in production. The healthcare product supplier\u2019s platform engineering team identified the highest-impact pipelines that should be ingested to the feature store.<\/span><\/p>\n

These pipelines were known as the pilot feature MVP. The MVP pipelines were brought into the feature store using the pertinent business definitions.\u00a0<\/span>\u00a0<\/span><\/p>\n

In addition, the MVP feature store used Unity Catalog within Databricks to handle critical\u00a0<\/span>data governance<\/span><\/a>\u00a0needs. Unity Catalog was used to apply governance to the machine learning models and to provide the basis for building data quality into the data pipeline process. Wavicle\u2019s team leveraged Unity Catalog\u2019s flexible platform to utilize several third-party applications for help with advanced profiling and data quality workflows and to provide a more automated data governance approach. The features that had been used for the pilot also now had clear business definitions and traceability.<\/span>\u00a0<\/span><\/p>\n

The pilot provided valuable information for the customer:<\/span><\/p>\n