# Data Mining B 88901079 B 88901132 Outline Why

- Slides: 24

Data Mining 第八組 B 88901079 萬佳育 B 88901132 葉書蘋

Outline Ø Why Data Mining Ø What is Data Mining Ø Data Mining Algorithm Ø Applications

Why Data Mining? (cont. ) Ø 資料雖多，了解卻少 Ø We are drowning in data, but starving for knowledge! Ø Solution l Data Mining Data warehousing CRM systems Web data Operational data

What Is Data Mining? Ø 資料採礦? ? Ø “Data mining is the process of exploration and analysis, by automatic or semi-automatic means, of large quantities of data in order to discover meaningful patterns and rules. ” l Mastering Data Mining by M. Berry/ G. Linoff--

From Data to Knowledge

The deciding factors for high school students to attend college are… All Students Attend College: 55% Yes 45% No IQ ? IQ=High IQ=Low Attend College: 79% Yes 11% No Attend College: 45% Yes 55% No Wealth Parents Encourage? Wealth = True Attend College: 94% Yes 6% No Parents Wealth = False Encourage = Yes Attend College: 69% Yes 21% No Attend College: 70% Yes 30% No Parents Encourage = No Attend College: 31% Yes 69% No

Data Mining的程序 Mining Model Training Data Mining Model To Predict DM Engine Mining Model Predicted Data

Data Mining 的 作循環

Data Mining Algorithm Ø Classification learning Ø Association learning Ø Clustering Ø Numeric prediction

Inferring rudimentary rules

Statistical modeling

Amazon

Amazon

Amazon

Amazon

e-Oscar

Software Ø Ø Ø Ø MLC++ (pd) MOBAL (pd) Emerald (rp) Kepler (rp) Clementine (cp) Data. Mind Data. Cruncher (cp) Darwin (cp) Intelligent Miner (cp) INSPECT (cp) Neo. Vista Solutions (cp) Nuggets (cp) Partek (cp) Polyanalyst (cp) SAS Data Mining (cp) Statiatica Ø Ø Ø Ø SGI Mind. Set (cp) Knowledge Explorer (cp) Data. Engine (cp) Delta Miner (cp) S-PLUS (cp) MATLAB (cp) Mathematica (cp) XGOBI (pd) Crystal Vision neé Explor. N sphinx. Vision Graf-FX IRIS Spotfire Netmap Visible Decisions Inc. Visual Mine

Reference l l l Data Mining：Practical Machine Learning Tools and Techniques with Java Implementations/Ian H. Written, Eibe Frank/The Morgan Kaufmann/October 1999 http: //www. datamining. org. tw http: //www. twocrows. com/glossary. htm http: //www. mkp. com/ http: //www. uniminer. com/center 01. htm http: //www. amazon. com