Title: Next Gen Data Mining: A Personal Viewpoint
1Next Gen Data MiningA Personal Viewpoint
2Thesis
- Data mining should aspire to become the
technology that allows entities to derive maximal
economic value from data while respecting the
sovereignty of data
3Quest What did we get right (if any)
4Abstraction of data mining operations from
applications
5Sins we committed
6Too timid in our ambition for data mining
7Didn't emphasize composability and integration
8Didn't desgin-in sovereignty of data
9Two contradictory views of Data Mining
10Not very valuable in practice
11Too powerful Ban it
12What gives?
13The way world sees it
14Collect Organize Data
Province of Data Management
15Extract value from Data
Province of Data Mining
Model Building Application Complex
Querying Search
16What should we do?
17Accept the mandate
18Approach
19Start with High-Value Applications
Distill Abstractions
Don't fall in the Quest traps
Don't limit to structured data Consider rich
operations Keep sight of composability
integration Design in data sovereignty
20An Application
21A grand challenge application
- Here is my data
- This is what I already know (priors)
- This is how I assign value
- Find for me that is valuable and
- too frequent
- too infrequent
- new and has changed since last interaction
- Allow me to intervene and guide the process
- Do it across sovereign entities
22Thesis
- Data mining should aspire to become the
technology that allows entities to derive maximal
economic value from data while respecting the
sovereignty of data
23Your tomatoes now
24- Next Generation Data mining should aspire to
become the technology that allows entities to
derive maximal economic value from data while
respecting the sovereignty of data. - Here is a grand challenge problem to drive the
future development of data mining - Here is my data
- This is what I already know (priors)
- This is how I assign value
- Find for me that is valuable and
- too frequent
- too infrequent
- new and has changed since last interaction
- Allow me to intervene and guide the process
- Do it across sovereign entities