Please use this identifier to cite or link to this item:
https://olympias.lib.uoi.gr/jspui/handle/123456789/38914Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Γεωργακοπούλου, Μαρία Άννα | el |
| dc.date.accessioned | 2025-04-07T09:31:37Z | - |
| dc.date.available | 2025-04-07T09:31:37Z | - |
| dc.identifier.uri | https://olympias.lib.uoi.gr/jspui/handle/123456789/38914 | - |
| dc.rights | CC0 1.0 Universal | * |
| dc.rights.uri | http://creativecommons.org/publicdomain/zero/1.0/ | * |
| dc.subject | Inflation | en |
| dc.subject | Forecasting | en |
| dc.subject | Machine Learning | en |
| dc.subject | Econometrics | en |
| dc.subject | Fixed effects | en |
| dc.subject | Random Forest | en |
| dc.subject | MAE | en |
| dc.subject | RMSE | en |
| dc.subject | MAPE | en |
| dc.title | «Inflation forecasting: Traditional vs. Modern predictive approaches» | en |
| dc.type | masterThesis | en |
| heal.type | masterThesis | el |
| heal.type.en | Master thesis | en |
| heal.type.el | Μεταπτυχιακή εργασία | el |
| heal.classification | Econometrics | en |
| heal.dateAvailable | 2025-04-07T09:32:37Z | - |
| heal.language | en | el |
| heal.access | free | el |
| heal.recordProvider | Πανεπιστήμιο Ιωαννίνων. Σχολή Οικονομικών και Διοικητικών Επιστημών | el |
| heal.publicationDate | 2025-03-26 | - |
| heal.abstract | Understanding the determinants of inflation is a critical issue in economic science due to its profound implications on monetary policy, economic stability, businesses, and financial institutions. This thesis analyzes the determinants of inflation and assesses different methodological approaches for its prediction, specifically comparing a Fixed Effects econometric model against Machine Learning (ML) methods in forecasting accuracy. Employing panel data covering 30 European countries from 1999 to 2019, this research examines the impact of macroeconomic variables, including unemployment, employment, industrial production, consumption, and the housing index, on inflation rates. The theoretical framework builds upon the Autoregressive Distributed Lag (ARDL) model, commonly utilized in macroeconomic analyses, while the primary econometric estimation method applied is the Fixed Effects Panel Data Model, chosen for its robustness in accounting for cross-country temporal variations. In parallel, ML techniques, notably Random Forests, were explored for their capacity to capture complex, non-linear interactions between variables, potentially offering superior predictive accuracy compared to traditional econometric methods. Model performances were evaluated using metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The comparative analysis reveals critical insights into both methodologies’ strengths and limitations, identifying key macroeconomic indicators significantly influencing inflation predictability. Findings suggest that integrating ML techniques alongside traditional econometric models may enhance inflation forecasting precision, offering valuable implications for economic policy and strategy formulation. | en |
| heal.advisorName | Μπεχλιούλης, Αλέξανδρος | el |
| heal.committeeMemberName | Σαλαμαλίκη, Παρασκευή | el |
| heal.committeeMemberName | Σταυρακούδης, Αθανάσιος | el |
| heal.academicPublisher | Πανεπιστήμιο Ιωαννίνων. Σχολή Οικονομικών και Διοικητικών Επιστημών. Τμήμα Οικονομικών Επιστημών | el |
| heal.academicPublisherID | uoi | el |
| heal.numberOfPages | 61 | el |
| heal.fullTextAvailability | true | - |
| Appears in Collections: | Διατριβές Μεταπτυχιακής Έρευνας (Masters) - ΟΕ | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Διπλωματική Εργασία Γεωργακοπούλου Μαρία Άννα .pdf | 1.09 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License
