Loading…
This event has ended. Visit the official site or create your own event on Sched.
Thank you for participating in Big Data Tech 2018! Access conference presentation decks here.
View analytic
Tuesday, June 5 • 9:00am - 9:45am
Transforming Medical Device Quality with Graph Data, Hadoop and Operationalized Analytics

Log in to save this to your schedule and see who's attending!

Feedback form is now closed.
A medical device at BSCI can consist of dozens of components, each of which contain many more sub-components. When a medical device fails its final inspection, how do we know which component was responsible for the failure? Until recently, engineers had to manually query relational data and build unwieldy pivot tables to identify problems.

In this talk, Eric Wespi will talk about building a solution from the ground up to save Boston Scientific millions of dollars, and enable Boston Scientific to manufacture better quality devices, faster.

In the first half, we will talk about graph databases in general and how we used neo4j, a graph database to build probability models for faster and better failure analysis. In the second half, we will talk about how we operationalized our analytics pipeline to enable a continuous value creation process. All too often, data science projects fail to operationalize their projects, thereby failing to obtain real value from their analysis. Boston Scientific and phData, however, marched towards a deployable solution and ultimately built a reliable data pipeline using Cloudera Hadoop, Spark, Kafka, and Streamsets

Speakers
avatar for Nipun Parasrampuria

Nipun Parasrampuria

Senior Data Engineer, PhData
avatar for Eric Wespi

Eric Wespi

Data Scientist, Boston Scientific


Tuesday June 5, 2018 9:00am - 9:45am
K1450 (Fireside Room) Normandale Partnership Center, 9700 France Ave So, Bloomington, MN 55431