《Oracle大数据解决方案》学习笔记9-1——数据库库内分析-快速交付彰显时间价值（In-Database Analytics: Delivering Faster Time to Value）

 

1. Oracle大数据工作流

2. Oracle库内分析架构

3. Oracle MoviePlex商店应用程序的界面 （这些元素在现在的腾讯视频应用中都有）

4.  词频分析可视化（标签云）

5.  数据挖掘及统计技术的应用场景

Sample Problem	Type of Problem	Algorithm	Applicability
Predict customer response to a marketing  campaign	Classification（分类）	1. Logistic Regression (GLM) 2. Decision Trees 3. Naïve Bayes 4. Support Vector Machine	1. Classical statistical technique Embedded within an application 2. Wide/narrow data/text
Predict the likely profitability of a new customer	Regression（回归）	1. Multiple Regression (GLM) 2. Support Vector Machine
Given customer response to a marketing campaign program, find the most significant predictors	Attribute Importance（属性重要性）	Minimum Description Length (MDL)	1. Attribute reduction 2. Identify useful data 3. Reduce data noise
Identify customer purchasing behavior that is significantly different from the norm	Anomaly Detection（异常检测）	One Class SVM	Quality control
Find the items that tend to be purchased together and specify their relationship— market basket analysis	Association Rules（关联规则）	A priori	Product grouping
Segment data into clusters and rank the probability that an individual will belong to a given cluster	Clustering（聚合）	1. Hierarchical K-Means 2. Hierarchical O-Means	1. Product grouping 2. Text mining 3. Gene analysis
Combining attributes into a new reduced set of features	Feature Extraction（特征提取）	Non-negative Matrix Factorization (NMF)	1. Text analysis 2. Feature reduction

6. Data mining extension for SQL Developer