SH111: Big Data - Use as a Predictor? Or Not?
Manage episode 444273467 series 3516753
In this episode, we discuss the potential and challenges of using Big Data to predict safety and performance issues, especially when human behavior is involved. While traditional cause-and-effect thinking works in some cases, complex incidents often involve many small contributing factors that are hard to detect. Big Data could help spot these hidden factors, but it requires detailed context and validation to ensure accuracy. Unlike structured fields like medicine, human behavior is unpredictable, influenced by culture, risk perception, and dynamic environments. While Big Data shows promise, it’s not yet ready to replace the experienced insights of human supervisors.
Original blog: https://www.thehumandiver.com/blog/big-data-use-as-a-predictor-or-not
Links: Article about Big Data: http://www.nytimes.com/2014/04/07/opinion/eight-no-nine-problems-with-big-data.html?_r=0
Todd Conklin’s Podcast: https://www.linkedin.com/pulse/leading-safety-metrics-big-data-prediction-todd-conklin
Tags: English, Gareth Lock, Safety, Safety Culture
132 つのエピソード