Gronloh, Riena Pribadi (2024) Model prediksi menggunakan machine learning: analisis faktor-faktor penentu customer churn di PT XYZ. Masters thesis, Universitas Pelita Harapan.
![Title [thumbnail of Title]](http://repository.uph.edu/style/images/fileicons/text.png)
Title_RIENA PRIBADI GRONLO 1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (279kB)
![Abstract [thumbnail of Abstract]](http://repository.uph.edu/style/images/fileicons/text.png)
Abstract_RIENA PRIBADI GRONLO 1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (593kB)
![ToC [thumbnail of ToC]](http://repository.uph.edu/style/images/fileicons/text.png)
ToC_RIENA PRIBADI GRONLO 1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter 1 [thumbnail of Chapter 1]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter1_RIENA PRIBADI GRONLO 1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter 2 [thumbnail of Chapter 2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter2_RIENA PRIBADI GRONLO 1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (2MB)
![Chapter 3 [thumbnail of Chapter 3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter3_RIENA PRIBADI GRONLO 1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter 4 [thumbnail of Chapter 4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter4_RIENA PRIBADI GRONLO 1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (3MB)
![Chapter 5 [thumbnail of Chapter 5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter5_RIENA PRIBADI GRONLO 1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (918kB)
![Bibliography [thumbnail of Bibliography]](http://repository.uph.edu/style/images/fileicons/text.png)
Bibliography_RIENA PRIBADI GRONLO 1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (793kB)
![Appendices [thumbnail of Appendices]](http://repository.uph.edu/style/images/fileicons/text.png)
Binder1.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (4MB)
Abstract
This study aims to identify the factors influencing customer churn at PT XYZ, a B2B
application-based company selling essential goods. Machine learning algorithms
such as Random Forest and Logistic Regression were used to predict churn based
on demographic and behavioral variables, including age, membership duration,
monthly transaction averages, spending value, and product variety. Transaction
data from January 2023 to August 2024 was analyzed to understand partner
behavior patterns. This study demonstrated that the Random Forest algorithm
achieved superior predictive performance in identifying potential customer churn
at PT XYZ, with an accuracy of 87.17%, precision of 74.40%, recall of 71.10%, and
an ROC-AUC score of 0.908. In comparison, Logistic Regression yielded an
accuracy of 78.07%, precision of 57.70%, recall of 33.30%, and an ROC-AUC
score of 0.733. This study provides strategic insights for PT XYZ to reduce churn
and maintain customer purchase retention through a data-driven approach. / Penelitian ini bertujuan untuk mengidentifikasi faktor-faktor yang memengaruhi
churn pelanggan di PT XYZ, sebuah perusahaan B2B berbasis aplikasi yang
menjual kebutuhan pokok. Algoritma machine learning seperti Random Forest dan
Regresi Logistik digunakan untuk memprediksi churn berdasarkan variabel
demografis dan perilaku pelanggan, seperti usia, lama keanggotaan, rata-rata
transaksi bulanan, nilai belanja, dan variasi produk. Data transaksi periode Januari
2023 hingga Agustus 2024 dianalisis untuk memahami pola perilaku mitra.
Penelitian ini menunjukkan bahwa algoritma Random Forest memiliki kinerja
prediktif yang unggul dalam mengidentifikasi potensi churn pelanggan di PT XYZ,
dengan akurasi sebesar 87,17%, precision 74,40%, recall 71,10%, dan skor ROCAUC
sebesar 0,908. Sebagai perbandingan, Regresi Logistik menghasilkan akurasi
sebesar 78,07%, precision 57,70%, recall 33,30%, dan skor ROC-AUC sebesar
0,733. Penelitian ini memberikan wawasan strategis bagi PT XYZ untuk
mengurangi churn dan mempertahankan retensi pembelian pelanggan melalui
pendekatan berbasis data.
Item Type: | Thesis (Masters) |
---|---|
Creators: | Creators NIM Email ORCID Gronloh, Riena Pribadi NIM01804230030 rienapribadi@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Achmadi, Hendra NIDN0321067002 UNSPECIFIED |
Uncontrolled Keywords: | Customer Churn ; Machine Learning ; Random Forest ; Regresi Logistik ; Prediksi ; PT XYZ ; Retensi Pembelian |
Subjects: | H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management |
Divisions: | University Subject > Current > Faculty/School - UPH Karawaci > Business School > Master of Management Current > Faculty/School - UPH Karawaci > Business School > Master of Management |
Depositing User: | Phillips Iman Heri Wahyudi |
Date Deposited: | 01 Mar 2025 05:46 |
Last Modified: | 01 Mar 2025 05:48 |
URI: | http://repository.uph.edu/id/eprint/67485 |