Page 363 - Proceeding The 2nd International Seminar of Science and Technology : Accelerating Sustainable Innovation Towards Society 5.0

nd
he 2 International Seminar of Science and Technology
“Accelerating Sustainable innovation towards Society 5.0”
ISST 2022 FST UT 2022
Universitas Terbuka

to RSUD dr. R. Soedjono Selong, however, the fulfillment of oxygen
needs for other hospitals in the province of NTB made the oxygen
supply allocation for dr. R. Soedjono Selong reduced [6].
There are several previous studies that used the Random Forest and
Decomposition method for forecasting including those conducted by
Primajaya & Sari [7] with the title Random Forest Algorithm for
Prediction of Precipitation, the results in this study are the MAE value
of 0.35, RMSE of 0.46, and accuracy of 99.45%. A similar study was
conducted by Siburian & Mulyana [8], namely the prediction of cell
phone prices using the Random Forest method, the result of this
research is the prediction accuracy rate using the Random Forest
method is 81%. Another study using the Decomposition method was
carried out by Satyawati et al [9] with the title prediction of the poor in
Indonesia using decomposition analysis, the results of this study
indicate that the additive decomposition model is better than the
multiplicative decomposition model, this is due to the accuracy of the
additive decomposition model (5 ,96%) is 10% smaller than the
multiplicative decomposition model. Based on these previous studies,
the purpose of this research is to see the results of predictions and
comparisons of the Random Forest and Decomposition methods on
the prediction of central oxygen supply at RSUD dr. Raden Soedjono
Selong.
2 METHODOLOGY
The data used in this study is secondary data, namely central oxygen
supply data at RSUD dr. Raden Soedjono Selong for the period from
January to November 2021. The data used is sourced from RSUD dr.
Raden Soedjono Selong. The method used in this research is the
Random Forest and Decomposition method with the help of R Studio
and Minitab software.
1.1 Random Forest
The Random Forest method is a development of the Classification and
Regression Tree (CART) method by applying the Boostrap
Aggregating (Bagging) and Random Feature Selection methods. In
conducting the analysis using Random Forest, there are no certain

326 ISST 2022 – FST Universitas Terbuka, Indonesia
International Seminar of Science and Technology “Accelerating Sustainable
Towards Society 5.0