I read a few articles claiming that the windshield was possibly hit by a bullet or rock, shortly before the deadly derailment. The FBI experts say that a broken windshield will exhibit different patterns, depending on whether it was hit by an impact (rock) or because of the crash. So from a data science point of view, how do you discriminate between

• Windshield hit by rock or bullet (making it a criminal case, possibly terrorism)
• Windshield cracked because of the force of the accident (making it looks like a suicidal or drugged driver, or mechanical failure, though terrorism is not necessarily ruled out)
• A combination of both

This is really an interesting root cause analysis problem for data scientists, involving pattern recognition and clustering techniques.

DSC Resources

• Career: Training | Books | Cheat Sheet | Apprenticeship | Certification | Salary Surveys | Jobs
• Knowledge: Research | Competitions | Webinars | Our Book | Members Only | Search DSC
• Buzz: Business News | Announcements | Events | RSS Feeds
• Misc: Top Links | Code Snippets | External Resources | Best Blogs | Subscribe | For Bloggers

Follow us on Twitter: @DataScienceCtrl | @AnalyticBridge