Mining Algorithm 정리

Top 10

• C4.5 (a kind of decision tree)
  • http://en.wikipedia.org/wiki/C4.5_algorithm
• k-Means
• SVM
• Apriori
  • http://en.wikipedia.org/wiki/Apriori_algorithm
  • a kind of association rule : http://en.wikipedia.org/wiki/Association_rule_mining
• EM
• PageRank
• AdaBoost
  • http://en.wikipedia.org/wiki/AdaBoost
  • adaptive boosting (http://goo.gl/hViJH), which is a machine learning meta-algorithm for performing supervised learning (http://goo.gl/3mC8y)
  • weak classifier를 결합하여 strong classifier를 구성
  • 이미지 처리할 때에 많이 쓰이는 알고리즘으로 training 단계를 거쳐 결과를 예측
• kNN
• Naive Bayes
• CART (Classification And Regression Tree)
• http://en.wikipedia.org/wiki/Decision_tree_lear

Public voting

- Decision Trees/Rules
- Regression
- Clustering
- Statistics (descriptive)
- Visualization
- Time series/Sequence analysis
- Support Vector (SVM)
- Association rules
- Ensemble methods
- Text Mining
- Neural Nets
- Boosting
- Bayesian
- Bagging
- Factor Analysis
- Anomaly/Deviation detection
- Social Network Analysis
- Survival Analysis
- Genetic algorithms
- Uplift modeling

Based on voting done by "Mahout user mailing list" here is the list:

- Matrix factorization (SVD)

- k-means

- Naive Bayes

- Dirichlet Process Clustering

- Matrix Factorization

- Frequent Pattern Matching

- LDA
- Expectation Maximization
- SVM
- Decision Trees
- Logistics Regression
- Random Forest