PENERAPAN SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE) UNTUK MENGATASI DATA IMBALANCED DALAM KLASIFIKASI KEJADIAN HUJAN MENGGUNAKAN METODE REGRESI LOGISTIK BINER

DESPALIA, VERTI MONA and Resti, Yulia and Zayanti, Des Alwine (2025) PENERAPAN SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE) UNTUK MENGATASI DATA IMBALANCED DALAM KLASIFIKASI KEJADIAN HUJAN MENGGUNAKAN METODE REGRESI LOGISTIK BINER. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_44201_08011182025018_cover .jpg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB) | Preview
	Text RAMA_44201_08011182025018.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_44201_08011182025018__TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_44201_08011182025018_0019077302_0004127001_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB)
	Text RAMA_44201_08011182025018_0019077302_0004127001 _02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (253kB) | Request a copy
	Text RAMA_44201_08011182025018_0019077302_0004127001 _03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13kB) | Request a copy
	Text RAMA_44201_08011182025018_0019077302_0004127001_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (380kB) | Request a copy
	Text RAMA_44201_08011182025018_0019077302_0004127001 _05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7kB) | Request a copy
	Text RAMA_44201_08011182025018_0019077302_0004127001_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (75kB) | Request a copy
	Text RAMA_44201_08011182025018_0019077302_0004127001_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (491kB) | Request a copy

Abstract

Classification on imbalanced data can affect the accuracy value of the classification and tends to ignore the minority class so that the prediction results will tend to the category. To overcome the problem of imbalanced data, synthetic minority oversampling technique (SMOTE) can be applied. This study aims to obtain an increase in classification accuracy by applying SMOTE to overcome imbalanced data in the classification of rain events using the binary logistic regression method. The data used is secondary data from the weather query builder dataset, namely daily data on rain events in Prabumulih City. The application of SMOTE to the binary logistic regression method for the classification of rain events resulted in an increase in the classification accuracy value in accuracy, precision and fscore, namely 0.27%, 0.91% and 0.04%, this shows that the application of SMOTE for the classification of rain events provides a better level of classification accuracy in accuracy, precision and fscore. While the level of classification accuracy in recall after the application of SMOTE decreased by 0.74%, this was caused by overfitting of synthetic data generated by SMOTE in the non-rain class which could make the model too focused on recognizing train data patterns, thus losing the ability to recognize patterns in test data.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	SMOTE, Imbalanced class, Binary Logistic Regression
Subjects:	H Social Sciences > HA Statistics > HA1-4737 Statistics H Social Sciences > HA Statistics > HA154-4737 Statistical data
Divisions:	08-Faculty of Mathematics and Natural Science > 44201-Mathematics (S1)
Depositing User:	Verti Mona Despalia
Date Deposited:	21 Mar 2025 08:15
Last Modified:	21 Mar 2025 08:15
URI:	http://repository.unsri.ac.id/id/eprint/169342

Actions (login required)

View Item