Course Syllabus
Titolo
Big Data Analytics per I Processi Decisionali
Argomenti e articolazione del corso
Nell'ultimo decennio stiamo assistendo ad un intesivo invenstimento in infrastrutture di business, le quali hanno migliorato considerevolmente le loro capacità di collezionare dati. Idealmente, possiamo affermare che molti aspetti del business sono legati ai dati ed è possibile analizzarne l'andamento mediante quest'ultimi: operazioni, manifattura, gestione della supply-chain. campagne di marketing, etc.
Questa ampia disponibilità di dati aziendali svolge ruolo di volano nello sviluppo di metodi per estrarre informazioni e conoscenza a supporto dei processi decisionali.
Questa attività richiede l'ausilio di figure tecniche, ma anche di esperti di dominio e di business. Da un lato, un tecnico può addestrare un software (o scrivere programmi) capaci di collazionare ed analizzare dati; dall'altro, gli esperti di dominio e di business svolgono un ruolo cruciale per permettere una corretta interpretazione del dato, considerando gli elementi caratterizanti in dominio.
Il corso intende fornire le conoscenze relative al cambio di paradigma sotteso alla data-driven organisation. Il corso, in particolare, intende fornire alcune competenze tecniche di base per la comprensione degli approcci di big data analytics e per supportare i diversi stakeholder nel processo di decisione.
Il corso è organizzato come segue
-
Introduction to BI and Big Data Analytics
-- Data Driven organization and Decision Making;
-- Big Data: Characteristics, opportunities and criticalities;
-- Understanding data driven organisations
-- The value of knowledge – digital economy and data driven decision making
-- The Structure and subsequent evolution of BI and Big Data Analytics systems -
The Evolution of BI Architectures (towards Big Data)
-- Decision Models on the basis of business functions
-- Definition, selection and metrics for computing directional indicators (KPI – CSF) -
The Big Data Lifecycle
-- Phases, methodologies and the value for business purposes (Data as value)
-- Models for data quality evaluation – structured data vs (unstructured) Big data (Lab: openrefine)
-- Models for data management and analytics – relational vs schema free (Lab: SQL and GraphDB)
-- Models and techniques for data analysis – how to use data for fact-based decision making
-- Visualisation models for decision making – selecting the proper model for each stakeholder – data story telling and indicators (Lab: Tableau) -
Getting value for Big Data Analytics
-- Understanding Machine learning: suvervised/unsupervised/metrics
-- ML tasks: classification/prediction/clustering
-- Basics of model evaluation -
Examples of Business Problems and Big Data Analytics solutions
Obiettivi
In accordo con il profilo professionale del corso di laurea, si ritiene che la conoscenza degli elementi fondanti della big data analytics in contesti di buisness rappresentino una risorsa preziosa per le figure in uscita dal percorso di studi, in particolare gli specialisti nelle risorse umane.
In termini di obiettivi di apprendimento, il corso intende fornire una conoscenza profonda degli elementi chiave (business, process e management) di soluzioni di big data analytics in contesti aziendali, insieme ad alcune nozione tecniche necessarie per comprendere i building block delle soluzioni BDA
Il corso intende promuovere l'apprendimento delle seguenti competenze trasversali:
• critical thinking
• ability to analyze and synthesize
• problem-solving
• team work
Metodologie utilizzate
Il corso prevede lezioni frontali alternate a metodologie didattiche attive (esercitazioni, progettazione, analisi di casi) per consentire agli studenti di relazionarsi con gli argomenti trattati presentando ed esplorando i propri punti di vista. Durante il corso si prevede di invitare specialisti nell'ambito per testimonianze di casi reali
Materiali didattici (online, offline)
• Slide;
• Casi di studio;
• Materiale didattico complementare e di approfondimento distribuito durante le lezioni
Materiali didattici (online, offline)
slide ed approfondimenti forniti dal docente (in accordo con la bibliografia)
Programma e bibliografia
La didattica per i frequentanti prevede un lavoro a casa (homework), volto a valutare le competenze dello studente in termini di (i) lavoro di squadra, (ii) comprensione dei dati e definizione di un modo per affrontare il problema, (iii) discussione della soluzione individuata e realizzata per l'utente finale. La valutazione dell'homework inciderà sulla valutazione finale dello studente
a) Provost, Foster, and Tom Fawcett. Data Science for Business: What you need to know about data mining and data-analytic thinking. " O'Reilly Media, Inc.", 2013,
-- Cap 1 Introduction: Data-Analytic Thinking
-- Cap 2 Business Problems and Data Science Solutions
-- Cap 10 Representing and Mining Text
b) Vikto Mayer-schonberger, Kenneth Cukier. "Una rivoluzione che trasformerà il nostro modo di Vivere e già minaccia la nostra libertà". Tutti i capitoli
c) Mezzanzanica and Mercorio, "Big Data as Fuel of Skill Intelligence", available at
https://link.springer.com/referenceworkentry/10.1007/978-3-319-63962-8_276-2
d) Alex Pentland, "Fisica Sociale", Chapters 5 and Appendix A
e) Gozzo, Pennisi, Asero, Sampugnaro. "Big Data e processi decisionali" Cap. 1
Modalità d'esame
Le prove d'esame sono organizzate come segue:
-- uno scritto, volto a valutare le competenze dello studente in termini di (i) concetti e metodologie acquisite (ii) capacità di impostare e identificare gli elementi chiave di un processo BDA e (iii) capacità di sintetizzare pro/contro del tecniche introdotte
-- prova orale (facoltativa su richiesta dello studente)
Orario di ricevimento
su appuntamento
Durata dei programmi
due anni accademici
Course title
Big Data Analytics for Decision Making Process
Topics and course structure
In the last decade, we have witnessed extensive investments in business infrastructure, which have improved the ability to collect data throughout the enterprise. Virtually every aspect of the business is open to data collection and often even instrumented for data collection: operations, manufacturing, supply-chain management, customer behaviour, marketing campaign performance, workflow procedures, etc.
Information is now widely available on external events such as market trends, industry news, and competitors’ movements. This broad availability of data has led to increasing interest in methods for extracting useful information and knowledge from data—the realm of data science.
However, extracting knowledge from data is far from straightforward and involves technical and non-technical users. On the one side, technicians can program (o train) algorithms to collect, process and analyse data; on the other side, business and domain experts are essential to guide to approach the right questions, bearing in mind the business characteristics and domain peculiarities.
Big data analytics solutions are designed to support business decisions and decision-making in such a context.
This course aims at providing knowledge about the paradigm shift behind the shift toward data-driven organisations, some (essential) technical competencies to understand the characteristics of big data analytics solutions (with labs), and finally to provide real-life examples of how big data analytics have been used to support a different kind of business decisions.
The course is organised as follows.
-
Introduction to BI and Big Data Analytics
-- Data Driven organization and Decision Making;
-- Big Data: Characteristics, opportunities and criticalities;
-- Understanding data driven organisations
-- The value of knowledge – digital economy and data driven decision making
-- The Structure and subsequent evolution of BI and Big Data Analytics systems -
The Evolution of BI Architectures (towards Big Data)
-- Decision Models on the basis of business functions
-- Definition, selection and metrics for computing directional indicators (KPI – CSF) -
The Big Data Lifecycle
-- Phases, methodologies and the value for business purposes (Data as value)
-- Models for data quality evaluation – structured data vs (unstructured) Big data (Lab: openrefine)
-- Models and techniques for data analysis – how to use data for fact-based decision making
-- Visualisation models for decision making – selecting the proper model for each stakeholder – data story telling and indicators (Lab: Tableau) -
Getting value for Big Data Analytics
-- Understanding Machine learning: suvervised/unsupervised/metrics
-- ML tasks: classification/prediction/clustering
-- Basics of model evaluation -
Examples of Business Problems and Big Data Analytics solutions
Objectives
According to the professional profile that the Degree Course intends to build, we consider that knowing how the key elements of a big data analytics project in a business context is a valuable resource for those who will deal with changing and unstable quality work contexts, as a specialist in HR, both in the field of work organization and training and professional updating.
As learning goals, the course aims at providing knowledge in deeply understanding the key (business, process, and management) elements of a big data analytics solution in a business setting, along with a basic knowledge of the technical issues involved.
The course aims to promote the following transversal skills:
• critical thinking
• ability to analyze and synthesize
• problem-solving
• team work
Methodologies
The course includes lectures alternating with active teaching methodologies (exercises, planning, case analysis) to allow students to relate to the topics covered by presenting and exploring their points of view. During the course, we plan to invite testimonials who are involved in bodies directly involved in structuring policies and training actions related to the world of work.
Educational materials (online, offline)
• Slides;
• Study cases;
• Complementary and in-depth didactic material distributed during the lessons
Online and offline teaching materials
slide ed additional materials provided by teacher (according to bibliography)
Programme and references
a) Provost, Foster, and Tom Fawcett. Data Science for Business: What you need to
the teachning includes a homework, aimed at evaluating the competencies of the student in terms of (i) teamwork, (ii) understanding the data and defining a way to approach the problem, (iii) discussing the solution identified and realised to the final user. The evaluation of the homework will affect the student's final score
know about data mining and data-analytic thinking. " O'Reilly Media, Inc.", 2013,
-- Cap 1 Introduction: Data-Analytic Thinking
-- Cap 2 Business Problems and Data Science Solutions
-- Cap 10 Representing and Mining Text
b) Vikto Mayer-schonberger, Kenneth Cukier. "Una rivoluzione che trasformerà il nostro modo di Vivere e già minaccia la nostra libertà". Tutti i capitoli
c) Mezzanzanica and Mercorio, "Big Data as Fuel of Skill Intelligence", available at
https://link.springer.com/referenceworkentry/10.1007/978-3-319-63962-8_276-2
d) Alex Pentland, "Fisica Sociale", Chapters 5 and Appendix A
e) Gozzo, Pennisi, Asero, Sampugnaro. "Big Data e processi decisionali" Cap. 1
Assessment methods
Exams are arganised as follows
-- a written, aimed at assessing the competencies of the student in terms of (i) concepts and methodologies acquired (ii) abilities in setting up and identifying key elements of a BDA process and (iii) abilities to summarise pros/cons of the techniques introduced
-- oral examination (optional, on demand)
Office hours
on appointment
Programme validity
two academic years
Staff
-
Fabio Mercorio
-
Mario Mezzanzanica