Preventatively reducing workplace injuries with data-driven insights

Overview

StrongArm Tech uses wearable devices generating roughly 1.2 million data points per day per person, ingested via the Databricks Data + AI Platform with Delta Lake and MLflow, to power machine learning Safety Scores that predict industrial injury risk. This reduced workplace injury rates by 60%, delivered $5.3M in gross savings for one customer, and cut the margin of error for evaluating injury risk by 78% (from 23% to 5%).

The challenge

StrongArm's goal is to capture every relevant data point roughly 1.2 million data points per day, per person to predict injuries and prevent these runaway costs from occurring. With such large volumes of time-series data flowing in real time, they struggled to build reliable and performant ETL pipelines that could scale to meet data science needs.

The solution

With the Databricks Data + AI Platform, data engineering, data science and analysts are able to more easily work on the data together. Delta Lake solved their data reliability issues, allowing them to easily ingest real-time IoT data. With data pipelines flowing seamlessly to the data science team, they were able to more easily innovate with machine learning that provides proprietary Safety Scores and classifications of activities to predict risk. MLflow streamlined the entire machine learning lifecycle, to ensure the best models make it to production.