Tesi etd-05122025-151849 |
Link copiato negli appunti
Tipo di tesi
Tesi di laurea magistrale
Autore
D'APOLI, CLARA
URN
etd-05122025-151849
Titolo
Interpretable Machine Learning for Time Series Forecasting: The Case of Natural Gas Consumption
Dipartimento
INFORMATICA
Corso di studi
DATA SCIENCE AND BUSINESS INFORMATICS
Relatori
relatore Prof. Guidotti, Riccardo
correlatore Dott. Spinnato, Francesco
correlatore Dott. Spinnato, Francesco
Parole chiave
- Data preprocessing
- Explainable Artificial Intelligence (XAI)
- Feature Engineering
- Global and Local Explanations
- Model Interpretability
- Natural Gas Consumption
- Regression-Based Models
- SHAP Values
- Shapelet Transform
- Sliding Window Technique
- Supervised Learning
- Time Series Forecasting
- Window Summarizer
Data inizio appello
30/05/2025
Consultabilità
Non consultabile
Data di rilascio
30/05/2028
Riassunto
The thesis addresses the challenge of predicting monthly Natural Gas consumption to mitigate the issue of irregular measurements faced by energy resellers, particularly for residential users. The goal is to develop accurate predictive models based on time series data. To this end, the study proposes a machine learning-based approach that adapts traditional regression models to time series forecasting using a supervised sliding window technique. This transformation allows high-performance tabular models to be applied together with Explainable AI (XAI) tools to make forecasts not only accurate but also interpretable. By improving transparency for energy suppliers and providing end users with a clearer view of their consumption behavior, the proposed solution contributes to more efficient, transparent and sustainable energy management, especially in the evolving context of smart meters and market liberalization.
File
Nome file | Dimensione |
---|---|
La tesi non è consultabile. |