1. Introduction to Data Mining
2.Data for Data Mining
3.Introduction to Classification: Naïve Bayes and Nearest Neighbour
4.Using Decision Trees for Classification
5.Decision Tree Induction: Using Entropy for Attribute Selection
6. Decision Tree Induction: Using Frequency Tables for Attribute Selection
7.Estimating the Predictive Accuracy of a Classifier
8.Continuous Attributes
9.Avoiding Overfitting of Decision Trees
1. Introduction to Data Mining
p 1 , 1.1 The Data Explosion
modern computer system – accumulating data – unimaginable rate
data increase หลายทาง เช่น
– current NASA Earth – terabyte , data everyday
– human genome project – storing เป็นพันๆ byte แต่ละ billion genetic bases
– data warehouse of customer transaction
– data record CCTV , credit card transaction
– 650 million website
– 900 million user FB , 3 billion posting a day
p 2, 150 million user ofTwitter , 350 million Tweet/day
data rich but knowledge poor
1.2 Knowledge discovery
non-trivial extraction implicit , previous unknown – potential ใช้ information จาก data โดยการใช้ data mining
2.Data for Data Mining
3.Introduction to Classification: Naïve Bayes and Nearest Neighbour
4.Using Decision Trees for Classification
5.Decision Tree Induction: Using Entropy for Attribute Selection
6. Decision Tree Induction: Using Frequency Tables for Attribute Selection
7.Estimating the Predictive Accuracy of a Classifier
8.Continuous Attributes
9.Avoiding Overfitting of Decision Trees