TY  - THES
N1  - Sri Utami Zuliana, S.Si., M.Sc., Ph.D.
ID  - digilib71770
UR  - https://digilib.uin-suka.ac.id/id/eprint/71770/
A1  - Faiqotul Muna, NIM.: 21106010040
Y1  - 2025/05/21/
N2  - Binary logistic regression is an analytical technique to see the relationship
between predictor variables and response variables. Meanwhile, Classification and
Regression Trees (CART) is a flexible decision tree method, capable of handling
non-linear relationships and interactions between variables automatically. In 2020,
there has been a COVID-19 pandemic that has an impact on the global economy,
including MSMEs in Indonesia, where some MSMEs have succeeded in increasing
revenue by utilizing digital platforms. This study compares the performance of
binary logistic regression and Classification and Regression Trees (CART) in classifying
factors that influence the increase in online business income using SUSENAS
data from BPS in 2021. The research method used is quantitative analysis with a
statistical approach. The results show that binary logistic regression has a classification
accuracy of 76.29% with an APER of 23.71%, while the Classification and
Regression Trees (CART) have a classification accuracy of 72.16% with an APER
of 27.84%. In conclusion, binary logistic regression shows better results in classifying
factors that increase online business income, especially if the relationship
pattern in the data is relatively linear and the model assumptions are met.
PB  - UIN SUNAN KALIJAGA YOGYAKARTA
KW  - Regresi Logistik Biner
KW  -  Classification and Regression Trees
(CART)
KW  -  Peningkatan Pendapatan
KW  -  Klasifikasi Data
M1  - skripsi
TI  - PERBANDINGAN MODEL REGRESI LOGISTIK BINER DAN METODE CLASSIFICATION AND REGRESSION TREES (CART) (STUDI KASUS: STATUS PENINGKATAN PENDAPATAN USAHA ONLINE PADA TAHUN 2020 TERHADAP TAHUN 2019 DI DIY)
AV  - restricted
EP  - 67
ER  -