Data Mashups -Data Science Summit
5 likes1,411 views
The document discusses the potential of data mashups in transforming underutilized data into actionable insights. It emphasizes the importance of diverse datasets and tools for data wrangling, such as Hadoop and Python, to uncover meaningful problems and patterns. By focusing on actionable results, data mashups can enable predictions and recommendations, ultimately turning data exhaust into valuable information.
Data Mashups -Data Science Summit
- 1. Data Mashups May 12, 2011 Data Scientist Summit Turning Data Exhaust into Pete Skomoroch LinkedIn Insights @peteskomoroch
- 2. We have an explosion of data • DataWrangling • InfoChimps • Data.gov • Factual • SimpleGeo
- 3. And the tools to make sense of it • Hadoop • NoSQL •R • Python • Mechanical Turk
- 4. Diverse datasets = better signal
- 7. Find a meaningful problem • Identify pain points • Work on stuff that matters • Focus on underutilized data http://www.flickr.com/photos/aloshbennett/
- 10. The best mashups are actionable • Reveal patterns • Enable predictions • Recommendations
- 11. Mashup: Skills & Cities
- 12. Yuba City, California: 21.3% Unemployment
- 13. Ames, Iowa: 4.7% Unemployment
- 14. Make data mashups work for you • Open Data = powerful mashups • Mashup > sum of its parts • Focus on meaningful problems • Actionable mashups are better