Siljanoska, Teodora and Savoska, Snezana and Blazheska-Tabakovska, Natasha (2025) A Comparative Methodological Framework for Semantic Enrichment of Time Series Forecasting: Beyond the Balkans Case Study. In: 15th International Conference on Applied Internet and Information Technologies (AIIT2025), November 7, 2025, Bitola, Macedonia.
|
Text
Time Series Forecasting.pdf - Published Version Download (738kB) |
Abstract
This research introduces a robust methodological framework that builds upon and extends our
prior investigations into knowledge extraction from time series data within the broader context
of digital transformation. Using the Balkans as a case study, we employ a comparative
methodological design to evaluate diverse forecasting techniques—VAR, ARIMA, LSTM, and
Prophet—integrated with semantic enrichment strategies. The proposed framework seeks to
address critical methodological gaps in interdisciplinary research that bridges machine
learning, econometric modeling, and semantic technologies. By systematically comparing
ontology engineering approaches and assessing semantic enrichment methodologies, we
develop a generalizable decision-support framework tailored for researchers engaged in
knowledge extraction from time series data. Our findings demonstrate that semantic
enrichment significantly enhances interpretability while maintaining forecasting accuracy
across different methodologies. Consequently, this study establishes methodological standards
and transferable guidelines that can inform and advance future interdisciplinary research in this
domain.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Scientific Fields (Frascati) > Natural sciences > Computer and information sciences |
| Divisions: | Faculty of Information and Communication Technologies |
| Depositing User: | Mrs Natasha Blazheska-Tabakovska |
| Date Deposited: | 23 Dec 2025 14:28 |
| Last Modified: | 23 Dec 2025 14:28 |
| URI: | https://eprints.uklo.edu.mk/id/eprint/11298 |
Actions (login required)
![]() |
View Item |
