The seminar will show how data scientists work in real-life scenarios and the process they set up to ensure rapid iteration on a problem. Given a problem statement of a power-load forecasting problem, attendants will learn how to approach a machine learning problem, from the definition of the error metrics and baselines to how to structure your code to deploy a maintainable and easy-to-evolve solution. The goal is to showcase the steps to move from the experimentation phase to a production-grade solution, through the use of simple and well-established coding principles. In particular, the seminar will focus on:
- A short introduction on what is a time series
- Simple exploratory data analysis for time-series data
- Understanding a problem statement and defining error metrics
- Delivery of a hackable, working solution with a baseline model
- Implementing a state-of-the-art model from the literature
- Hands-on implementation and execution of a new model directly in the codebase
Intervengono
Luca BAGGI, AI Engineer @xtream
Marco SIMONTE, AI Scientist @xtream
Il seminario si colloca all’interno del corso di Laboratorio di Programmazione edizione 2025/2026 ed è indirizzato a studenti del secondo/terzo anno dei Corsi di Laurea Triennale e del secondo anno dei Corsi di Laurea Magistrale, in particolare per le Classi di Laurea L-35 (Scienze matematiche) e LM-91 (Tecniche e metodi per la società dell'informazione).
PER INFORMAZIONI
Prof. Daniele Toti
E-mail: daniele.toti@unicatt.it
