Machine Learning for Business Analytics
DATES TBC
DURATION: 6 training sessions + Project Work
LECTURER: Guido Sanguinetti, Professor of Applied Physics at SISSA and Visiting Faculty at MIB Trieste School of Management
This intensive course bridges advanced data science, artificial intelligence, and business strategy with a focus on insurance applications.
You'll work with leading researchers from SISSA to master both the mathematical foundations and practical business implementations of machine learning algorithms.
The course emphasizes hands-on learning through laboratories and a comprehensive project work where you'll apply supervised and unsupervised learning techniques to real business scenarios.
Critical attention is given to the ethical dimensions of ML deployment, ensuring you can navigate the complex landscape of algorithmic fairness, transparency, and accountability.
Three core sections:
DURATION: 6 training sessions + Project Work
LECTURER: Guido Sanguinetti, Professor of Applied Physics at SISSA and Visiting Faculty at MIB Trieste School of Management
This intensive course bridges advanced data science, artificial intelligence, and business strategy with a focus on insurance applications.
You'll work with leading researchers from SISSA to master both the mathematical foundations and practical business implementations of machine learning algorithms.
The course emphasizes hands-on learning through laboratories and a comprehensive project work where you'll apply supervised and unsupervised learning techniques to real business scenarios.
Critical attention is given to the ethical dimensions of ML deployment, ensuring you can navigate the complex landscape of algorithmic fairness, transparency, and accountability.
Three core sections:
- Foundations of ML: linear regression, unsupervised learning (k-means, PCA), and feature selection
- Supervised learning algorithms: logistic regression, decision trees, random forests, and neural networks
- Ethics and business application: critical analysis of ML bias, fairness issues, and customer-centric insurance analytics
