74972 - Decision Support Systems

Learning outcomes

Business analytics, con terminologia corrente. Al termine del corso, che adotta un approccio orientato alle applicazioni, lo studente acquisisce competenze scientifiche e tecnologiche necessarie alla progettazione, sviluppo e messa in uso di un sistema di supporto alle decisioni in contesti aziendali reali. Questo comporta: - lavorare su dati aziendali reali, analizzando quali siano i problemi gestionali coinvolti e come risolverli. - lo studio dei dati per mezzo di statistica e analisi operazionale, - la applicazione di tecniche di ottimizzazione con l’obiettivo di orientare pianificazione e processo decisionale, - lo studio di algoritmi di ottimizzazione euristici e metauristici, - la formazione di modelli predittivi, - la comunicazione dei risultati ottenuti (a clienti, colleghi o partner) tramite piattaforme diverse. Verrà progettato e sviluppato assieme codice specifico, con attenzione alla possibilità di deploy su piattaforme mobile e web.

Course contents

Operational analytics from a.y. 2022/23. The course provides the tools to predict short/medium term management data and to optimize processes for allocating scarce resources based on predicted data. Elements of predictive analytics and heuristic optimization will be presented and integrated.
For the predictive part, the course proposes methodologies and techniques to analyze, model and predict univariate or multivariate time series, with data typically generated by IoT networks or by logs of management processes.
The data obtained will be elements of mathematical models of management processes in which to optimize the allocation of scarce resources.
The proposed tools will be used in real business application cases.
The scientific contributions concern the knowledge needed to develop an operational analytics module on data obtained from a business information system, and concern statistical and optimization skills applied to business process modeling. In particular will be addressed:
- stochastic models, random variables. probability distributions
- predictive models: statistical (ARMA, ARIMA, SARIMA) and neural models (feedforward, feedback, deep learning)
- performance indicators and descriptive statistics
- simple models of integer programming
- metaheuristic solving techniques
The technological contributions will be functional to the practical implementation of the mentioned module, which will be done standalone in python, although other environments and architectures are suggested.
The module will be set up in the classroom and completed independently by each student, and may constitute the project for the exam.

Readings/Bibliography

Lecture slides.

Maniezzo, Vittorio, Boschetti, Marco Antonio, Stützle, Thomas: Matheuristics, Algorithms and Implementations. Springer International Publishing (2021). (only to deepen the topics)

Teaching methods

I will teach in the lab as much as I will be allowed to, in order to ensure hands-on experience of the proposed methods.

We will also visit a company, which will propose us an actual problem, related to the course contents. We will work together on it, and we will present our results by the end of the course.
The algorithms will be coded, following the students' choice, in c# or python. The web / mobile modules will be implemented in javascript and html5.

“As concerns the teaching methods of this course unit, all students must attend Module 1, 2 [https://www.unibo.it/en/services-and-opportunities/health-and-assistance/health-and-safety/online-course-on-health-and-safety-in-study-and-internship-areas] on Health and Safety online”.

Assessment methods

The course provides both scientific and technological skills that will be tested through the presentation of a specific project for each student. During the course will be provided elements relevant to the program listed above, each of which originates a possible application of an algorithmic or systems nature that can contribute to the definition of a unitary computer solution. The exam will consist of the presentation of the solution that each student will have individually developed. The proposed solution must be able to run on the machines in the labs, and therefore also on my course server.

Typically, unless otherwise agreed upon, the project will be a python solution. No jupyter notebooks are accepted, only pandas, numpy and matplotlib can be used as additional libraries, unless otherwise explicitly agreed upon.

Teaching tools

Slides and lecture notes. They will be downloadable before the corresponding lesson.

Links to further information

http://isi-personale.csr.unibo.it/vittorio.maniezzo/didattica/DSS/SistSuppDec.html

Office hours

See the website of Vittorio Maniezzo