Course 2023-2024 a.y.

• Data management architectures: a brief overview.
• Data understanding and data preparation.
• Models and statistical techniques applied to Big Data.
  • Linear and logistic regression.
  • Regression and classification trees.
  • Time series analysis.
  • Machine learning algorithms and neural networks.
• Models' performance evaluation.
• Applications and real cases using open-source software (KNIME and R) in the following areas: internet of things, social & web content analysis, customer relationship management, fraud detection and operations.

Get the following competences:

• Big Data ingestion and management.
• Data preparation and cleaning.
• Machine learning algorithms application.
• Machine learning model evaluation.

• Improve his 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.

• Face-to-face lectures
• Guest speaker's talks (in class or in distance)
• Exercises (exercises, database, software etc.)
• Case studies /Incidents (traditional, online)
• Group assignments

In the course two different approaches are used: theoretical and applicative. A number of machine learning data analysis case histories are shown, on Big and Small Data, using specific machine learning software (Knime and R). At the end of the course, students are able to reply all the analysis by themselves.

It is based both on a group assignment (to be developed during the course and submitted before the end of the lessons; 50% of the final grade) and on an individual final written exam (50% 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).

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.

• M. KUHN, K. JOHNSON, Applied predictive modeling, Springer, 2013.
• Teacher's slides.