Data driven decisions need high quality data. The risk of making incorrect decisions based on wrong, inadequate, or missing data is too high, and it can have devastating consequences. Operations can often experience numerous data issues, including flatlines, outliers, noise changes, abrupt changes, correlation breaks, etc. so what can be done? The sheer magnitude of data makes this an extremely difficult problem to solve . Millions of PI tags with millions of samples per second and thousands of critical uses of the data.
With the rapid growth of sensors, data, and users, a focused journey towards good data quality has never been more important. More and more decisions are data driven; those decisions need good data. So what’s your plan? Have you tried building in-house tools to address data quality? Have you used custom functions in PI to identify some data issues? Or do you employ your data scientists to clean the data instead of focusing on deriving business value from the data?
In this session, Jonas Hellgren, CEO of APERIO and Jane Arnold, Industry Expert, will discuss the magnitude and impact of data quality in data-driven decision making, share some real-life examples of failures due to poor data quality, and finish with an approach to improving data quality.