Laureano Gallardo con Data Mining and Statistical Analysis: Case Study with R code: Statistical programming with software R
1. Problem Description and Data Available
2. The "Pre-Process of date" and scan data
3. Selection of variables.
3.1.1. Correlation between numeric variables using a graph.
3.1.2. Correlation between numerical variables with the variable class.
3.1.3. Correlation between numerical and categorical variables.
3.1.4. Correlation between categorical variables and the dependent variable Class.
4. Prediction models.
4.1. Logistic regression models.
4.2. Decision trees.
5. Neural networks
6. Comparison, model and final conclusions