Exploratory analysis
0 likes312 views
The document discusses tools for data analysis and building intelligence including Metabase, an open source business intelligence tool used by over 21,000 companies daily. It focuses on speeding up the time it takes to answer questions from data through automation and building a "data scientist in a box". The goal is to answer 80% of questions from data in under 20 minutes to facilitate real-time exploration and problem solving.
Exploratory analysis
- 1. simon@metabase.com @sbelak Exploratory analysis: automation, augmentation, and building tools for thought
- 2. Goal: answer 80% of questions stemming from data in <20min
- 3. The analytics chasm 2 min 20 min project Ideal. Almost real-time. Can be done during brainstorming without disrupting the flow. :( Added to roadmapSqueeze in somewhere in the day
- 4. Doing our job better is often a matter of speed and quantity
- 5. Metabase ❤ github.com/metabase/metabase • Open source BI/analytics tool • Runs on-premise, data-agnostic • 21k+ companies use us daily • Focus on UX and friendliness • Building a “data scientist in a box”
- 6. Metabase ❤ github.com/metabase/metabase • Open source BI/analytics tool • Runs on-premise, data-agnostic • 21k+ companies use us daily • Focus on UX and friendliness • Building a “data scientist in a box”
- 7. From artificial intelligence to augmenting human intelligence
- 8. Flow
- 9. Affordances of our tools shape how we approach problems
- 14. Factor out the mechanical part of the analysis
- 15. Nils, wrong encodings, outliers, input errors
- 16. Every aggregated metric is a mixture of all your segments
- 17. A lot of problems are also time series problems (we just don’t treat them as such)
- 18. Changes in distribution a r e h i n t s a b o u t underlying changes in segment mixture
- 19. Declarative analysis: Directing focus, rather than specifying the steps
- 22. REPL + notebook + Metabase?