Aristotle University Of Thessaloniki (AUTH)
AI-driven agricultural commodity price forecasting with hybrid models and scalable data infrastructure
Abstract
dc:descriptionThe aim of the present doctoral thesis was the study and development of machine learning methodologies for agricultural commodity price forecasting, with emphasis on grain commodities such as corn, wheat, and rice. Initially, a systematic literature review of the international scientific literature was conducted in order to identify and evaluate the forecasting techniques used in agricultural economics, including traditional statistical models, machine learning methods, ensemble learning approaches, and deep learning techniques. Subsequently, the main data sources affecting agricultural commodity prices were examined, including historical price series, weather data, production indicators, news and social sentiment data, as well as macroeconomic variables. In parallel, a scalable data warehouse architecture was designed and implemented for the management of large-scale agricultural data using big data technologies and distributed processing infrastructures. The research also focused on the comparison of different forecasting algorithms in terms of predictive accuracy, scalability, and generalization capability on real-world time series datasets. Furthermore, issues related to data preprocessing, feature selection, and model evaluation were analyzed with the objective of developing reliable forecasting systems for decision support in the agricultural sector. The findings of this thesis highlight the importance of advanced machine learning techniques and integrated data infrastructures in improving agricultural price forecasting and supporting agricultural economic analysis.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Theofilou, Asterios
- Θεοφίλου, Αστέριος
Subjects
dc:subject × 18- Πρόβλεψη τιμών αγροτικών εμπορευμάτων
- Τεχνητή νοημοσύνη
- Μηχανική μάθηση
- Κλιμακούμενη αρχιτεκτονική αποθήκης δεδομένων
- Agricultural commodity price forecasting
- Artificial intelligence
- Machine learning
- Scalable data warehouse
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Φυσικές Επιστήμες
- Γεωπονία, Δασολογία και Αλιεία
- Γεωπονικές Επιστήμες και Κτηνιατρική
- Γεωπονία, διεπιστημονική προσέγγιση
- Computer and Information Sciences
- Natural Sciences
- Agriculture, Forestry and Fisheries
- Agricultural and Veterinary Sciences
- Agriculture, interdisciplinary
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/61646