Forecasting COVID-19 impact on RWI/ISL container throughput index by using SARIMA models
| Autor: | Kaan Koyuncu, Umut Arican, Leyla Tavacioglu, Neslihan Gökmen |
|---|---|
| Přispěvatelé: | MÜ, Datça Kazım Yılmaz Meslek Yüksekokulu, Ulaştırma Hizmetleri Bölümü, Koyuncu, Kaan |
| Rok vydání: | 2021 |
| Předmět: |
2019-20 coronavirus outbreak
Index (economics) Coronavirus disease 2019 (COVID-19) Operations research Computer science Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Geography Planning and Development 0211 other engineering and technologies Ocean Engineering Transportation 02 engineering and technology Management Monitoring Policy and Law Domino SARIMA Maritime trade 0502 economics and business Throughput (business) 050210 logistics & transportation 021103 operations research 05 social sciences COVID-19 RWI/ISL Container (abstract data type) Financial crisis containers Forecasting |
| Zdroj: | Maritime Policy & Management |
| ISSN: | 1464-5254 0308-8839 |
| DOI: | 10.1080/03088839.2021.1876937 |
| Popis: | Maritime operators are facing their biggest challenge called Coronavirus (COVID-19) since the 2008 financial crisis. As part of the measures taken by the countries against the virus, the domino effect started with the breaks in the interconnected supply chain, like the spider web. The main purpose of this study is modeling the Institute of Shipping Economics and Logistics (ISL) and the Leibniz-Institut für Wirtschaftsforschung (RWI) Container Throughput Index with the time series, to reveal the relationship between the short-term forecast results and the COVID-19 seen in the first months of 2020. The deep effect of COVID-19 on maritime trade is investigated by forecasting the RWI/ISL Container Throughput Index in 89 major international container ports, including and excluding seasonal variations. The modeling process of the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing State Space Model (ETS) is explained. To evaluate SARIMA and ETS models’ performance, information criteria, and error measurements are calculated and compared. SARIMA model is found as more suitable model than ETS forecasting seasonally and working-day adjusted and original RWI/ISL. The results indicated that the SARIMA model is suitable and efficient for the forecasting of RWI/ISL. Three months’ forecasting results are showed that the decrease will continue. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|