Meningkatkan keterlibatan customer lifetime value di industri sepeda motor menggunakan model ensemble machine learning

Vinsens, Marselus (2024) Meningkatkan keterlibatan customer lifetime value di industri sepeda motor menggunakan model ensemble machine learning. Masters thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
[FINAL] File Tesis - Marselus Vinsens-title_MARSELUS VINSENS.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (31kB)
[thumbnail of Abstract] Text (Abstract)
[FINAL] File Tesis - Marselus Vinsens - ABSTR_MARSELUS VINSENS.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (313kB)
[thumbnail of ToC] Text (ToC)
[FINAL] File Tesis - Marselus Vinsens - ToC_MARSELUS VINSENS.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (134kB)
[thumbnail of Chapter 1] Text (Chapter 1)
[FINAL] File Tesis - Marselus Vinsens - Chapt_1 MARSELUS VINSENS.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (705kB)
[thumbnail of Chapter 2] Text (Chapter 2)
[FINAL] File Tesis - Marselus Vinsens - Chapt_ 2 MARSELUS VINSENS (1).pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter 3] Text (Chapter 3)
[FINAL] File Tesis - Marselus Vinsens - Chapt_3 MARSELUS VINSENS (2).pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (780kB)
[thumbnail of Chapter 4] Text (Chapter 4)
[FINAL] File Tesis - Marselus Vinsens - Chapt_4 MARSELUS VINSENS (3).pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)
[thumbnail of Chapter 5] Text (Chapter 5)
[FINAL] File Tesis - Marselus Vinsens - Chapt_5 MARSELUS VINSENS (4).pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (231kB)
[thumbnail of Bibliography] Text (Bibliography)
[FINAL] File Tesis - Marselus Vinsens - Bibli_MARSELUS VINSENS.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (493kB)
[thumbnail of Appendices] Text (Appendices)
[FINAL] File Tesis - Marselus Vinsens - Appen_MARSELUS VINSENS.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)

Abstract

Predicting Customer Lifetime Value (CLV) is a critical task for businesses in the motorcycle industry, as it enables effective customer engagement and strategic decision-making. This study explores the use of ensemble machine learning models, namely Random Forest and XGBoost, to enhance the accuracy and reliability of CLV predictions. Leveraging transactional data from a motorcycle business, the research employs a comprehensive methodology that includes data cleansing, feature engineering, and predictive modelling to address the complexities of customer behaviour and purchasing patterns. The performance of the models was assessed using evaluation metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). Among the tested models, Random Forest demonstrated superior performance with an R² of 0.98 and the lowest MAE, indicating its exceptional predictive accuracy and robustness. Feature importance analysis identified transaction frequency, average order value, and cumulative spending as the most significant contributors to CLV, providing actionable insights for optimizing customer relationship strategies. This research highlights the potential of ensemble learning models to transform CLV prediction in the motorcycle industry. By offering accurate and interpretable results, these models empower businesses to implement data-driven marketing strategies, improve customer retention, and maximize profitability. The findings serve as a valuable resource for organizations seeking to leverage advanced analytics to gain a competitive advantage in the dynamic market landscape. / Memprediksi Customer Lifetime Value (CLV) adalah tugas penting bagi bisnis di industri sepeda motor, karena memungkinkan peningkatan keterlibatan pelanggan dan pengambilan keputusan strategis. Penelitian ini mengeksplorasi penggunaan ensemble machine learning model, yaitu Random Forest dan XGBoost, untuk meningkatkan akurasi dan keandalan prediksi CLV. Dengan memanfaatkan data transaksi dari bisnis sepeda motor, penelitian ini menerapkan metodologi komprehensif yang mencakup pembersihan data, rekayasa fitur, dan pemodelan prediktif untuk mengatasi kompleksitas perilaku dan pola pembelian pelanggan. Kinerja model dievaluasi menggunakan metrik seperti Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), dan koefisien determinasi (R²). Dari model yang diuji, Random Forest Regression menunjukkan kinerja terbaik dengan nilai R² sebesar 0,98 dan MAE terendah, menandakan akurasi prediksi yang unggul dan keandalannya. Analisis pentingnya fitur mengidentifikasi frekuensi transaksi, nilai rata-rata pesanan, dan pengeluaran kumulatif sebagai faktor utama dalam CLV, memberikan wawasan yang dapat ditindaklanjuti untuk mengoptimalkan strategi hubungan pelanggan. Penelitian ini berfokus kepada potensi ensemble machine learning model dalam mentransformasi prediksi CLV di industri sepeda motor. Dengan menyediakan hasil yang akurat dan dapat diinterpretasikan, model-model ini memungkinkan bisnis untuk mengimplementasikan strategi pemasaran berbasis data, meningkatkan retensi pelanggan, dan memaksimalkan profitabilitas. Temuan ini menjadi sumber daya yang berharga bagi organisasi yang ingin memanfaatkan analitik canggih untuk mendapatkan keunggulan kompetitif di pasar yang dinamis.
Item Type: Thesis (Masters)
Creators:
Creators
NIM
Email
ORCID
Vinsens, Marselus
NIM01679220002
mvinsens@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Murwantara, I Made
NIDN0302057304
UNSPECIFIED
Uncontrolled Keywords: Customer Lifetime Value ; Machine Learning ; Ensemble Learning ; Random Forest ; XGBoost ; Industri Sepeda Motor ; Analitik Prediktif
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7885-7895 Computer engineering. Computer hardware
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > School of Information Science and Technology > Master of Informatics
Current > Faculty/School - UPH Karawaci > School of Information Science and Technology > Master of Informatics
Depositing User: Phillips Iman Heri Wahyudi
Date Deposited: 28 Feb 2025 04:08
Last Modified: 28 Feb 2025 04:08
URI: http://repository.uph.edu/id/eprint/67430

Actions (login required)

View Item
View Item