CD Skripsi

Penerapan Smote Dan Ensemble Learning Untuk Penanganan Data Tidak Seimbang Pada Analisis Klasifikasi Rumah Layak Huni Di Provinsi Riau

---

ABSTRACT
Imbalanced data is one of the problems in classification analysis which can impact the decreasing of the classification performance. The imbalanced data give the bad impact to classification performance, because mostly ignore the minority class. This final project discusses the application of SMOTE and Ensemble Learning (Bagging and Boosting) for handle imbalanced data in classification analysis depends on inhabitable house data in Riau province from Badan Pusat Statistik in 2020. The results showed that the data balanced with SMOTE obtained accuracy, sensitivity, specificity, G - Mean, and AUC of values 76.54%, 71.65%, 82.80%, 77.02%, dan 77.22%. Bagging obtained accuracy, sensitivity, spesificity, G-mean, and AUC of values 94.32%, 71.66%, 98.35%, 83.95%, dan 85.01%. Boosting obtained accuracy, sensitivity, specificity, G-mean, and AUC of values 94.26%, 72.06%, 98.20%, 84.12% dan 85.13%. This showed that Bagging performance to handle imbalanced data is better than Boosting and SMOTE.
Keywords: Imbalanced data, SMOTE, bagging, boosting, livable house.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

1903113593

Penerbit

Pekanbaru : Universitas Riau – FMIPA – Statistika., 2023

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

1903113593

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

STATISTIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

TIAR

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar