Advanced Analytics in a Big Data World (E-learning)

📅 Self-Paced E-learning course
🌍 English

Overview

Business Knowledge Series course

Presented by Bart Baesens, Ph.D. Professor at the School of Management of the University of Southampton (UK); or Christophe Mues, Ph.D., Professor at the School of Management of the University of Southampton (UK); or Cristian Bravo, Ph.D, Assistant Professor, Business Analytics, University of Southampton (UK); or Wouter Verbeke, Ph.D., Assistant Professor, Business Informatics, University of Brussels (Belgium); or Stefan Lessmann, Ph.D., Professor, School of Business and Economics, Humboldt University (Germany)

The E-learning course starts by refreshing the basic concepts of the analytics process model: data preprocessing, analytics and post processing. We then discuss decision trees and ensemble methods (bagging, boosting, random forests), neural networks, support vector machines (SVMs), Bayesian networks, survival analysis, social networks, monitoring and backtesting analytical models. Throughout the course, we extensively refer to our industry and research experience. Various business examples (e.g. credit scoring, churn prediction, fraud detection, customer segmentation, etc.) and small case studies are also included for further clarification. The E-learning course consists of more than 20 hours of movies, each 5 minutes on average. Quizzes are included to facilitate the understanding of the material. Upon registration, you will get an access code which gives you unlimited access to all course material (movies, quizzes, scripts, ...) during 6 months. The E-learning course focusses on the concepts and modeling methodologies and not on the SAS software. To access the course material, you only need a laptop, iPad, iPhone with a web browser. No SAS software is needed.

Learn how to

apply a series of powerful, recently developed, cutting-edge analytical and data science techniques
ensure the practical application of these techniques to optimize strategic business processes and decision making
explore a futuristic vision of how emerging data science techniques might change your key business processes
deploy, monitor, and optimally backtest analytical models.

Course Outline

Refresher: The Analytics Process Model

basic nomenclature (definition of customer, definition of target, and so on)
data collection and preprocessing (sampling, missing values, outliers, weights of evidence, and so on)
predictive versus descriptive analytics (data mining)
putting analytics to work
analytic model requirements (performance, interpretability, operational efficiency, compliance)
key application areas (CRM, risk management, fraud, online analytics)

Refresher: Decision Trees

splitting/stopping/assignment decision
key algorithms: C4.5 (See5), CART, CHAID
recommendations for using decision trees in a business context

Regression Trees

splitting/stopping/assignment criteria
case study: using regression trees for loss forecasting

Ensemble Methods

bootstrapping
bagging
boosting
stacking
random forests

Alternative Rule Representation Formats

rule types (propositional, oblique, M-of-N, fuzzy, and so on)
decision tables (lexicographical ordering, contraction methods, and so on)
decision diagrams
case study: decision tables and diagrams for customer scoring
case study: decision tables for textual knowledge verification

Neural Networks

multilayer perceptrons (MLPs)
MLP types (RBF, recurrent, and so on)
weight learning (backpropagation, conjugate gradient, and so on)
overfitting, early stopping, and weight regularization
architecture selection (grid search, SNC, and so on)
input selection (Hinton graphs, likelihood statistics, brute force, and so on)
self-organizing maps (SOMs) for clustering
case study: using SOMs for country corruption analysis

Support Vector Machines (SVMs)

linear programming
the kernel trick and Mercer theorem
SVMs for classification and regression
multiclass SVMs (one- versus-one, one-versus-all coding)
hyperparameter tuning using cross-validation methods
case study: benchmarking SVM classifiers

Opening up the Neural Network and SVM Black Box

business applications of neural networks and SVMs
rule extraction methods (pedagogical versus decompositional approaches such as neurorule, neurolinear, and trepan)
two-stage models (combining white-box linear models with black-box high-performing neural networks)
case studies

Bayesian Network Classifiers

Naive Bayes
tree augmented Naive Bayes (TAN)
unrestricted Bayesian network classifiers
Bayesian inference
case study: Bayesian networks for churn prediction

Survival Analysis

censoring
survival probabilities versus hazard rates
Kaplan Meier analysis
parametric survival analysis
proportional hazards regression
time varying covariates
competing risks
neural networks for survival analysis
case study: survival analysis for Customer Lifetime Value (CLV) modeling

Social Network Learning and Inference

implicit versus explicit social networks
learning using networked data
key application areas (Facebook/Twitter, churn, fraud, online analytics, and so on)
Markov random fields
homophily (guilt by association)
local classifiers
relational classifiers (relational neighbor, probabilistic relational neighbor, relational logistic regression, and so on)
Featurization
collective inference (Gibbs sampling, iterative classification, and so on)
case study: using social networks for churn detection in a telco context

Monitoring and Backtesting Analytical Models

quantitative versus qualitative model monitoring
model backtesting (model stability, model discrimination, model calibration, binomial/Hosmer-Lemeshow test, traffic light indicator approach, impact of macro-economic effects)
model benchmarking (internal versus external benchmarking, benchmarking statistics)
qualitative validation of analytical models (data quality and master data management, model design, documentation, involvement of management and corporate governance)
case study: backtesting a customer scoring model

Other Learning Algorithms and Applications (Short)