Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/30264| Title: | Prediksi Customer Lifetime Value dengan Menggunakan Random Forest Regressor |
| Other Titles: | Customer Lifetime Value Prediction Using Random Forest Regressor |
| Authors: | Sembiring, Sri Dwi Afriani |
| metadata.dc.contributor.advisor: | Lubis, Andre Hasudungan |
| Keywords: | Customer Lifetime Value;Random Forest Regressor;Prediksi;Prediction |
| Issue Date: | Feb-2026 |
| Publisher: | Universitas Medan Area |
| Series/Report no.: | NPM;228160041 |
| Abstract: | Customer Lifetime Value (CLV) merupakan salah satu indikator penting dalam bisnis yang digunakan untuk mengukur nilai keuntungan jangka panjang yang dihasilkan oleh seorang pelanggan. Prediksi CLV diperlukan agar perusahaan dapat mengidentifikasi pelanggan yang paling bernilai serta menyusun strategi pemasaran dan pengambilan keputusan bisnis secara lebih efektif. Namun, karakteristik data pelanggan yang kompleks dan memiliki hubungan non-linear menyebabkan metode konvensional kurang optimal dalam memprediksi nilai CLV. Oleh karena itu, penelitian ini bertujuan untuk menerapkan algoritma Random Forest Regressor (RFR) dalam memprediksi nilai CLV. Data penelitian terdiri dari tiga fitur utama, yaitu purchase_history, tenure, dan total_spent, dengan variabel target berupa nilai CLV.data dibagi menjadi data latih dan data uji untuk membangun serta mengevaluasi model prediksi. Kinerja model sendiri dievaluasi menggunakan metrik Mean Square Error (MSE), R-squared (R2), dan Mean Absolute Error (MAE), untuk mengukur tingkat kesalahan prediksi dan kemampuan model dalam menjelaskan variasi data. Pada hasil penelitian menunjukkan model RFR sangat akurat dengan nilai R2 sebesar 0,9973 yang artinya model mampu menjelaskan sebesar 99,73% variasi data CLV. Namun, tingkat kesalahan prediksi dapat dilihat dari nilai MSE sebesar 348.525 dan MAE sebesar 354,46. Hasil menjelaskan bahwa algoritma RFR terbukti efektif dan akurat dalam memprediksi CLV dan dapat digunakan untuk pengambilan keputusan bisnis sebagai strategi perusahaan. Customer Lifetime Value (CLV) is a crucial business indicator used to measure the long-term profit generated by a single customer. Predicting CLV is essential because it helps companies identify their most valuable customers, allowing them to create more effective marketing strategies and better business decisions. However, customer data is often complex and has non-linear relationships, which makes conventional methods less effective at predicting CLV accurately. Because of this, this study aims to apply the Random Forest Regressor (RFR) algorithm to get better results in predicting CLV. The research data uses three main features: purchase_history, tenure, and total_spent, with CLV as the target variable. The data was split into training and testing sets to build and evaluate the prediction model. To see how well the model performs, it was evaluated using three main metrics: Mean Square Error (MSE), R-squared (R2), and Mean Absolute Error (MAE). These metrics help measure the prediction error and the model's ability to explain the data's variation. The results show that the RFR model is highly accurate, with an R2 value of 0.9973, which means the model can explain 99.73% of the variation in the CLV data. Even though the MSE is 348,525 and the MAE is 354.46, these error rates are actually very low when compared to the overall scale of the predicted CLV values. In conclusion, the RFR algorithm proves to be an effective and reliable tool for predicting CLV. It can be used as a helpful resource to support a company's strategic business decision-making. |
| Description: | 37 Halaman |
| URI: | https://repositori.uma.ac.id/handle/123456789/30264 |
| Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 228160041 - Sri Dwi Afriani Sembiring - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 902.23 kB | Adobe PDF | View/Open |
| 228160041 - Sri Dwi Afriani Sembiring - Chapter IV.pdf Restricted Access | Chapter IV | 425.6 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.