Computational Analysis of GDP, Inflation, and Unemployment Trends in the Western Balkans
Session
Computer Science and Communication Engineering
Description
Using computational econometric techniques, this study examines three important macroeconomic indicators over a multi-year period: GDP growth, inflation, and unemployment. The study uses a Python-based analytical pipeline for data processing, visualization, and interpretation by integrating cross-sectional and time-series data from trustworthy sources. The methodology evaluates indicator behavior under different economic conditions by using statis- tical learning and segmentation across multiple temporal phases. Based on the research outcomes, traditional macroeconomic frameworks, such as Okun's Law and the Phillips Curve, exhibit limited predictive accuracy across heterogeneous economic environments, particularly when incorporating the effects of global disruptions. The research presents a modular analytical framework for real-time monitoring of macroeconomic dynamics, emphasizing the necessity for flexible, data-driven policy approaches. By integrating economic theory with computa- tional modeling, the study advances the development of scalable decision-sup- port systems, enhancing resilient governance in environments characterized by uncertainty, structural heterogeneity, and exogenous volatility.
Keywords:
GDP, Inflation, Unemployment, Comparative Analysis, Economic Indicators
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-982-41-2
Location
UBT Lipjan, Kosovo
Start Date
25-10-2025 9:00 AM
End Date
26-10-2025 6:00 PM
DOI
10.33107/ubt-ic.2025.102
Recommended Citation
Krasniqi, Adea and Neziri, Vehbi, "Computational Analysis of GDP, Inflation, and Unemployment Trends in the Western Balkans" (2025). UBT International Conference. 34.
https://knowledgecenter.ubt-uni.net/conference/2025UBTIC/CS/34
Computational Analysis of GDP, Inflation, and Unemployment Trends in the Western Balkans
UBT Lipjan, Kosovo
Using computational econometric techniques, this study examines three important macroeconomic indicators over a multi-year period: GDP growth, inflation, and unemployment. The study uses a Python-based analytical pipeline for data processing, visualization, and interpretation by integrating cross-sectional and time-series data from trustworthy sources. The methodology evaluates indicator behavior under different economic conditions by using statis- tical learning and segmentation across multiple temporal phases. Based on the research outcomes, traditional macroeconomic frameworks, such as Okun's Law and the Phillips Curve, exhibit limited predictive accuracy across heterogeneous economic environments, particularly when incorporating the effects of global disruptions. The research presents a modular analytical framework for real-time monitoring of macroeconomic dynamics, emphasizing the necessity for flexible, data-driven policy approaches. By integrating economic theory with computa- tional modeling, the study advances the development of scalable decision-sup- port systems, enhancing resilient governance in environments characterized by uncertainty, structural heterogeneity, and exogenous volatility.
