Introduction to predictive analytics
- Data Mining and Machine Learning
- Classification, Regression, Clustering, Association
- Use of Predicative Analytics to solve business problems
- The Crisp-Dm process
- Predicative analytics vs prescriptive analytics
The preparation of data
- categorical variables and quantitative variables
- Management of missing values
- Create the input variables
- reduction of dimensionality
- Normalization of data
Algorithms
- Naive Bayes
- Decision Trees
- Support Vector Machines
- Neural Networks
- K-means clustering
- Hierarchical Clustering
- Association Rules (Aprori Algorithm)
- ensemble
The evaluation of the models
- Training & Test Set
- The confusion matrix
- the metrics for the evaluation of the classification
- Roc curves
- Cross validation
Some houses studies
- Churn Analysis
- Fraud Detection
- Marketing Campaign Targeting