ML for Innovation Research: PhD/DBA Seminar
Welcome to the documentation for the ML for Innovation Research seminar — a hands-on 2×3-hour program teaching PhD/DBA students how to apply machine learning as a research tool for innovation studies.
8
Modules
2
Sessions
6
Hours
PhD
Level
Hands-on seminar teaching PhD/DBA students to apply ML techniques — clustering, NLP, classification, and generative AI — to real innovation research questions using a synthetic Swiss Innovation Survey dataset.
Modules
01
The Map
The map — ML paradigms, workflow, dataset
02The Discovery Branch
Discovery branch — K-Means, PCA, UMAP
03The Text Branch
Text branch — VADER, TF-IDF, LDA
04Where Branches Cross
Crossing branches — cross-tabulation, synthesis
05The Prediction Branch
Entering prediction — recap, supervised learning
06The Prediction Branch
Testing theory — Random Forest, Logistic, ROC/AUC
07Beyond the Tree
Extending the map — LLMs, prompts, structured output
08The Complete Map
Complete map — decision framework, thesis patterns