Course 2025-2026 a.y.

21035 - PREDICTIVE AND GENERATIVE AI FOR BUSINESS DECISIONS

Department of Decision Sciences

Course taught in English

Student consultation hours
31
ACME (6 credits - II sem. - OP  |  SECS-S/01) - AFC (6 credits - II sem. - OP  |  SECS-S/01) - AI (6 credits - II sem. - OP  |  SECS-S/01) - CLELI (6 credits - II sem. - OP  |  SECS-S/01) - CLMG (6 credits - II sem. - OP  |  SECS-S/01) - DES-ESS (6 credits - II sem. - OP  |  SECS-S/01) - DSBA (6 credits - II sem. - OP  |  SECS-S/01) - EMIT (6 credits - II sem. - OP  |  SECS-S/01) - ESS (6 credits - II sem. - OP  |  SECS-S/01) - FIN (6 credits - II sem. - OP  |  SECS-S/01) - GIO (6 credits - II sem. - OP  |  SECS-S/01) - IM (6 credits - II sem. - OP  |  SECS-S/01) - MM (6 credits - II sem. - OP  |  SECS-S/01) - PPA (6 credits - II sem. - OP  |  SECS-S/01)
Course Director:
LUCA MOLTENI

Classes: 31 (II sem.)
Instructors:
Class 31: LUCA MOLTENI


Suggested background knowledge

Students are expected to have basic knowledge of descriptive and inferential statistics.

Mission & Content Summary

MISSION

The course provides an overview of the integration and analysis process of structured and unstructured data (Big Data), focusing on the most important applications of predictive and generative AI in managerial issues. The contents of the course covers both technical aspects of predictive AI and more interpretation related topics (how to translate the analytical outputs into meaningful business insights); furthermore the course will introduce some selected use cases of generative AI in business.

CONTENT SUMMARY

1) Predictive AI 

  • Data management architectures: a brief overview.
  • Data understanding and data preparation.
  • Machine Learning Models and Statistical Techniques applied to Small and Big Data for business decisions:
    • Logistic regression.
    • Regression and classification trees.
    • Random Forest
    • Gradient Boosting
    • Neural networks and Deep Learning
    • ARIMA Models
  • Models' performance evaluation.
  • Applications and real cases using open-source software (KNIME and R) in the following areas: social & web content analysis, customer relationship management, fraud detection and operations, IOT and anomaly detection

2) Generative AI

  • Introduction to LLM
  • Opportunities and limits related to generative AI in business application
  • Selected use cases: chatbot, document management, content creation

Intended Learning Outcomes (ILO)

KNOWLEDGE AND UNDERSTANDING

At the end of the course student will be able to...

Get the following competences:

  • Small/Big Data ingestion and management
  • Data preparation and cleaning
  • Predictive AI/ Machine learning algorithms application
  • Predictive AI/Machine learning model evaluation
  • Main Generative AI applications in business

APPLYING KNOWLEDGE AND UNDERSTANDING

At the end of the course student will be able to...

Improve his/her skills to manage and to take advantages of the huge availability of data nowadays produced by a great variety of sources, using one of the machine learning software preferred by data scientists and to leverage generative AI for selected applications in business


Teaching methods

  • Lectures
  • Guest speaker's talks (in class or in distance)
  • Practical Exercises
  • Collaborative Works / Assignments

DETAILS

The student will solve many business problems working on selected use cases.

 

Part of the exam will be dedicated to a Group Assignmnt on a use cases selected by students with the teaxher approval.


Assessment methods

  Continuous assessment Partial exams General exam
  • Written individual exam (traditional/online)
     x
  • Collaborative Works / Assignment (report, exercise, presentation, project work etc.)
 x    

ATTENDING STUDENTS

It is based both on a group assignment (to be developed during the course and submitted before the end of the lessons; 60% of the final grade) and on an individual final written exam (40% of the final grade), proposed in a reduced version compared to the full not-attending exam.

 

With the written exam we test the technical knowledge of the students,with the assignment the ability to manage and to take advantages of the availability of data from a great variety of sources, using one of the machine learning software preferred by data scientists (Knime).


NOT ATTENDING STUDENTS

Individual final written exam (100% weight).

 

With the closed question we test the technical knowledge of the students, with the open questions the ability to interpret the results emerging from the application of the analytical software proposed in the course and to evaluate the quality of alternative machine learning models.


Teaching materials


ATTENDING AND NOT ATTENDING STUDENTS

F. ACITO, Predictive Analytics with KNIME, Springer, 2023

Teacher's Slides and Use Cases

Last change 28/05/2025 16:06