Salta al contenuto principale della pagina

MODELLING AND IDENTIFICATION

CODE 108766
ACADEMIC YEAR 2022/2023
CREDITS
  • 6 cfu during the 1st year of 8734 INGEGNERIA GESTIONALE (LM-31) - GENOVA
  • SCIENTIFIC DISCIPLINARY SECTOR ING-INF/04
    TEACHING LOCATION
  • GENOVA
  • SEMESTER 1° Semester
    TEACHING MATERIALS AULAWEB

    OVERVIEW

    The course presents the main modelling techniques for complex dynamical processes related to financial engineering. Moreover, the course addresses the identification methods necessary to evaluate the parameters present in the presented models.

    AIMS AND CONTENT

    LEARNING OUTCOMES

    Knowing the main modelling classes for dynamic processes with attention to those adopted in management engineering; defining a class of candidate models for a specific dynamic process; knowing the features of a parameter identification problem; designing the solution of an identification problem; analyzing the convergence properties of the adopted solution algorithm.

    AIMS AND LEARNING OUTCOMES

    The learning outcomes of the course refer to the capacity of:

    • understand the dynamic features of a process;
    • define a model suitable for representing the process and fulfil the objectives of the required analysis;
    • knowing the features of an identification problem;
    • knowing the most important classes of identification models;
    • designing the solution of an identification problem.

    PREREQUISITES

    The course prerequisites refer to basic elements of systems theory, statistics and optimization.

    TEACHING METHODS

    The course consists in lessons during which the theoretical contents of the course are presented together with the solution of numerical cases and the use of some software frameworks related to the course topics.

    SYLLABUS/CONTENT

    Definition of the main features of dynamic systems and to the main modelling classes. Introduction to the most important dynamic models adopted in management engineering and financial engineering.

    Identification techniques: definition of the parameter identification problem, model families (ARX, ARMAX, OE,  ARXAR, BJ),  MPE identification: convergence theorems, identification for ARX models (least squares identification), for ARMAX models and for ARXAR models, batch and iterative algorithms.

    RECOMMENDED READING/BIBLIOGRAPHY

    L. Ljung, "System Identification: Theory for the user", Prentice Hall (2nd Edition), 1999.

    TEACHERS AND EXAM BOARD

    Exam Board

    SIMONA SACONE (President)

    LESSONS

    Class schedule

    All class schedules are posted on the EasyAcademy portal.

    EXAMS

    EXAM DESCRIPTION

    The exam is an oral presentation.

    ASSESSMENT METHODS

    During the exam the student has to present the main arguments of the course, to solve numerical exercises and to explain the theoretical notions necessary for their solution