Predicting the Costs of Forwarding Contracts: Analysis of Data Mining Competition Results

• Autorzy: Janusz Andrzej , Jamiołkowski Antoni , Okulewicz Michał

Identyfikatory

DOI

10.15439/2022F303

• Konferencja: Federated Conference on Computer Science and Information Systems (17 ; 04-07.09.2022 ; Sofia, Bulgaria)
• Języki publikacji: EN

Abstrakty

EN

We describe an international data mining competition FedCSIS 2022 Challenge: Predicting the Costs of Forwarding Contracts that was organized in association with the FedCSIS conference series at the KnowledgePit platform. We explain the competition scope and briefly discuss the results obtained by the most successful teams. We also share the most interesting findings of our post-competition research assisted by the BrightBox technology, and describe our own prediction model that was used as the competition baseline. Finally, we show the results of our experiment conducted with the solution ensembling mechanism provided by KnowledgePit. The goal of this experiment was to find a mixture of submitted predictions that is the most accurate estimation of real execution costs of forwarding contracts.

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2022
• Tom: Vol. 30
• Strony: 399--402
• Opis fizyczny: Bibliogr. 20 poz.

Twórcy

autor

Janusz Andrzej

autor

Jamiołkowski Antoni

autor

Okulewicz Michał