Datamart analysis with Machine Learning (ML)

Here's the link to the application : 📈 Visual Analytics for ML and the 📕 report.pdf containing a case study for interpreting your results.

Summary :

Development of a predictive model for the "display" variable using Machine Learning techniques by transforming all continuous variables into categorical for modeling.

1. Data Presentation

Description and descriptive analysis of qualitative and quantitative variables, and their transformation for analysis.

2. Multiple Component Analysis (MCA)

Use of MCA to reduce data dimensionality, identification of principal components, and their interpretation.

3. Modeling

• Decision Tree: Used for classification with specific parameters and a confusion matrix to assess performance.
• Random Forest: Application of the random forest approach, parameter setting, and classification results.
• Logistic Regression: Prediction using logistic regression, details on error rates, and predictions.

4. Model Comparison

Comparative analysis of three machine learning models : Decision Tree, Random Forest and Logistic Regression.

5. Model Performance (Analysis of the best model)

Evaluation of the performance of different models in terms of precision and sensitivity.