R is one of the most popular open source language of programming for statistical computing. The aim of this module is to provide students with a common ground for data analysis in R. Learn more at: www.r-project.org 

Instructor: Paolo Racca

Coding in Python covers the basic elements of the widely used programming language and focuses on management and analysis of databases. Python is an object-oriented language developed under an OSI-approved open source license, making it freely usable and distributable, even for commercial use. Learn more at: www.python.org 

Instructor: Paolo Racca

The module presents basic statistical and mathematical tools used in economics and business analytics, including concepts of probability, hypothesis testing, matrix calculation and multivariate calculus.

Instructor: Consuelo Nava


The module provides students with theoretical and analytical background knowledge for the understanding of economies as complex adaptive systems. Through classes dedicated to the exploration of different micro-founded modeling tools, and to the discussion of seminal models, the course promotes the development of critical spirit and a trans-methodological view in respect to microeconomic theories, models and paradigms.

Instructor: Magda Fontana

The module trains in building and analyzing social networks in an agent-based perspective. In addition to traditional network theory, the course will introduce decentralized and autonomous emergence of networks mainly using Slapp (Swarm-Like Agent Protocol in Python), Netlogo and NetworkX library (in Python).

Learn more at: https://github.com/terna/SLAPP

Instructor: prof. Pietro Terna and Marton Karsai

The core idea is that many (if not most) phenomena in the world can be effectively modeled with agents, an environment and a description of agent-agent and agent-environment interactions. An agent is an autonomous individual or object with particular properties, actions and possibly goals. The environment is the landscape on which agents interact and can be geometric, network-based, or drawn from real data. Interaction affects the internal states of agents, their actions and the environment.

The goal of the module is to introduce the making of agent-based simulation models, comparing NetLogo and SLAPP.

Instructor:  prof. Pietro Terna and Matteo Morini

The module focuses on structuring (initializing, scheduling, and designing), coding and analysing agent-based models mainly in Netlogo. Netlogo is an agent-based programming language and integrated modeling environment software. It is free and open source.

Learn more at: http://ccl.northwestern.edu/netlogo/

Instructor:  Magda Fontana

Data mining has often been considered a set of techniques aimed at exploring data functional to a proper quantitative analysis. The evolution of IT technologies and the growing availability of structured and unstructured data give data scientist the opportunity to extract information and value by merging statistics and artificial intelligence. The science of data unleashes a huge potential to apply sophisticated algorithms to discover pattern, classify features and objects, build networks and to predict different and apparently unrelated social and economic phenomena.

Instructors: prof. Paolo Giudici and Paola Cerchiello

Machine learning has become pervasive in our societies without knowing in different technological application, from search engines to industrial robots. The course provides the theoretical and analytical tool to explore and apply a range of techniques including supervised (parametric/non-parametric algorithms, support vector machines, kernels, neural networks) and unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). The approach based on case studies allows students to test their validity and limitation to different problems in economics and business intelligence.

Instructor: Ruggero Pensa and Roberto Esposito



The module is aimed at developing technical instruments for the analysis of microeconomic data. In particular, starting form main features of linear models we introduce a new class of statistical models for the study of discrete choices (binary and multinomial) and counts in cross-section data.
Moreover, to take into account heterogeneity and/or unobserved effects, we extend previous models accordingly to the introduction of individual specific and/or choice specific effects, modelled as random. In such framework, models both for cross-section and panel data will be discussed. Finally, a preliminary introduction to a Bayesian version of these models is proposed.

Instructor: prof

This course if focused on the direct, hands-on application of the theoretical knowledge developed in previous courses. Classes take place in the lab, where students will learn how to perform with R both database manipulation and advanced statistical analysis. R is an open source statistical language, which include the richest availability of packages for statistical analysis and big data manipulation. The use of real word data example of managerial decisions, internet of things, consumers classification, risk analysis make possible for student to have a direct experience of the main critical issues in data analysis. wCoding in Phython and R is the required language competence both in companies and in academia.

Instructor:  Consuelo Nava

In the the process of data analytics the phase of visualization allows an effective comprehension, dissemination and use of outcomes also beheyond the restrict circle of data scientists. The module aims at providing an introduction to data visualization with a focus on reporting and charting information using the Python matplotlib library. The course starts with a design and information literacy perspective, touching on what makes a good and bad visualization, and what statistical measures translate into in terms of visualizations. The second part focuses on the technological aspects of matplotlib, describing the gamut of functionalities and the variety of statistical plots helping learners to identify when a particular method is good for a particular problem.

Instructor: Rossano Schifanella

Innovation is the key strategic leverage for established firms, entrepreneur, and startups in the present very competitive business environment. This course provides MADAS students with an in-depth knowledge of the actors involved in the process of innovation with a focus on R&D processes, best practices in intellectual property rights and strategy for research alliance and joint venture. Data at the firm level such as balance sheet and patent data form a large source of information to be used and analyzed for sound data driven business decisions.

Instructor: prof. Aldo Geuna

The Lab focuses on the analysis of technology and innovation using patent data. Patent data provide a very rich set of information on the technological activities of individual inventors and companies. They are increasingly used to map technologies and monitor markets for business intelligence. They can be used as indicators of innovation in regions and countries. Based on weekly exercises, students learn to use the patent databases and handle the details to interpret correctly the richness of the data. A specific focus is dedicated to relational data like patent collaborations and patent citations and the related networks.

Instructor: prof. Fabio Montobbio

The rise of big data has provided researchers with new possibilities to understand and predict consumer behaviour. Consumer analytics based on structured and unstructured data is at the core of this course. Students will take home how to describe, explain, and predict customer behaviour by analysing different case studies. From co-evolving social and technological innovations, the big data revolution contributes to increase efficiency in the technical delivery of goods and services, to generate social and economic value for the consumers and, not last, to make better business decision.

Instructor: prof. Marco Guerzoni

The combination of connectivity and digitalization have the potential to dramatically enhance participation of consumers to co-create, co-produce and inoculate their own values into what they consume. In this lab students will use different techniques and methodologies learned in over the first semester to solve problems related to business analytics in particular in the field of marketing, finance and risk. The hands-on approach allows to deal with real dataset and to extract, analysis and visualize information to draw an advanced profiling of costumers or to predict trends and behaviour.  

Instructor: Vittorio Carlei and Stefano Terzi

This course focuses on the notion of smart cities as laboratory for innovation. Spatial  and real-time data are dramatically changing urban economies not only providing citizens with opportunities to become smarter consumers, but also opening up opportunities for innovation in the framework of circular and sharing economy. The course explores these new challenges at different levels:

  • Capture and storage of spatial data;
  • Simulation of urban systems;
  • Urban planning, policy and governance;

Instructor: Massimiliano Nuccio

Web and social media analytics are quite diffused in the digital marketing and business intelligence fields, since they foster customer engagement and open up dramatic opportunities for a long-term relationship with consumers. In cities, they are becoming even more important in the provision of urban services, like transports and mobility, energy and health because public administration can improve the quality of their services and their efficiency by monitoring the digital information grasp by sensors. Students will interact with unstructured data by applying, among the others, text mining, geo-localization and sentiment analysis.

Instructor: Fabrizio Dominici and Claudio Rossi