Bart Baesens

← Back to courses

Crash Course in Data Science

📅 March 20th, 2019
🌍 English

Course outline (9am-5pm)

  • Definitions
  • Examples
    • X-selling
    • Credit scoring
    • Fraud Detection
    • Recommender system
    • Customer journey analysis
  • Analytics Process Model
    • Data scientist
    • Key definitions (customer, target, etc.)
  • Data Preprocessing
    • Types of data
    • Types of variables
    • Denormalizing data
    • Sampling and Exploratory analysis
    • Missing values
    • Outlier detection and handing
    • Categorization
    • Variable transformation
  • Types of Analytics
    • Predictive Analytics
      • Linear regression
      • Logistic regression
      • Decision trees
      • Random forests
      • Neural networks (deep learning)
      • Other predictive analytics techniques
    • Evaluating Predictive Models
      • Performance measures for classification models
        • Out of sample versus Out of time
        • Cross-validation
        • Classification accuracy, classification error, sensitivity, specificity, precision, recall, F-measure
        • Receiver Operating Characteristic curve (ROC)
        • Area under Receiver Operating Characteristic curve (AUC)
        • Cumulative Accuracy Profile (CAP)
        • Accuracy ratio (Gini)
        • Lift curve
        • Top-decile lift
        • Performance benchmarks
      • Performance measures for regression models
        • Scatter plot
        • Pearson correlation
        • R-squared
        • Mean Squared Error (MSE)
        • Mean Absolute Deviation (MAD)
      • Other performance measures for predictive analytical models
        • Interpretability
        • Operational efficiency
        • Economical cost
    • Descriptive Analytics
      • Association rules
        • Support
        • Confidence
        • Post-processing
        • Applications (recommender systems)
      • Sequence rules
        • Support
        • Confidence
        • Applications (customer journey analysis, process analytics)
      • Clustering
        • Hierarchical clustering
          • Distance measures (Euclidean, Manhattan)
          • Agglomerative versus divisive methods
          • Dendrogram
        • Non-hierarchical clustering
          • k-means clustering
        • Evaluating clustering solutions
      • Social Network Analytics
        • Social Network Examples (churn, credit card fraud, identity theft)
        • Social Network Definitions
          • Nodes versus edges
        • Social Network Metrics
          • Geodesic
          • Degree
          • Closeness
          • Betweenness
          • Graph theoretic center
        • Social Network Learning
          • Featurization
  • Post Processing of Analytical models
    • Model Interpretation (Visual Analytics, Sankey plots, Traffic light indicator approach, Nomograms, Decision tables)
    • Model Documentation
    • Model Backtesting
    • Model Benchmarking
    • Model Stress Testing
    • Model Deployment
    • Model Governance
    • Model Ethics
  • Economic Perspective
    • Total Cost of Ownership (TCO)
    • Return on Investment (ROI)
    • In- versus Outsourcing
    • On-Premise versus Cloud Analytics
    • Open Source versus Commercial Software
  • Improving ROI
    • New sources of data
    • Data quality
    • Management support
    • Cross-Fertilization
  • Privacy and Security
    • Overall considerations
    • RACI Matrix
    • Accessing Internal Data
    • Privacy Regulation (GDPR)
👩‍🏫 Lecturers

Prof. dr. Wouter Verbeke
Professor at KU Leuven

Prof. dr. Bart Baesens
Professor at KU Leuven

🏢 Location

Van der Valk Hotel Brussels Airport (Belgium)

Culliganlaan 4b
1831 Diegem
Belgium
hotelbrusselsairport.com

🏫 Organizer

Bart Baesens

💼 Register

This course is in the past, registration is no longer possible.


Price and Registration

This course is in the past, registration is no longer possible.