Prediksi Keberhasilan Menindaklanjuti Pelanggan pada Dealer Mobil dengan Komparasi Algoritma Random Forest dan XGBoost
Abstract
The automotive industry is facing intense competition in boosting vehicle sales, where the follow-up process with prospective customers plays a crucial role in sales conversion. This study develops a predictive model for the success of follow-ups at car dealerships by comparing two machine learning algorithms: Random forest and XGBoost. A dataset of Honda car dealership customers from 2023 was processed through a preprocessing stage, including handling data imbalance and encoding categorical data. The models were evaluated using accuracy, precision, recall, and F1-score metrics. The results show that XGBoost outperforms with an accuracy of 91.67%, compared to Random forest's 88.89%. Both models demonstrate balanced performance across positive and negative classes, indicating a significant improvement over previous approaches. This study recommends expanding the dataset and developing a prediction-based decision support system to enhance the marketing effectiveness of car dealerships.
Keywords: Machine learning; Random forest; XGBoost
Abstrak
Industri otomotif menghadapi persaingan ketat dalam meningkatkan penjualan kendaraan, di mana proses tindak lanjut (Follow-up) kepada calon pelanggan menjadi faktor krusial dalam konversi penjualan. Penelitian ini mengembangkan model prediksi keberhasilan Follow-up pada dealer mobil dengan membandingkan dua algoritma machine learning, yaitu Random forest dan XGBoost. Dataset pelanggan dealer mobil Honda tahun 2023 diproses melalui tahap preprocessing, termasuk penanganan ketidakseimbangan data menggunakan encoding data kategorikal. Model dievaluasi menggunakan metrik akurasi, precision, recall, dan F1-score. Hasil menunjukkan XGBoost unggul dengan akurasi 91,67%, lebih baik dibanding Random forest dengan akurasi 88,89%. Kedua model menunjukkan performa yang seimbang pada kelas positif dan negatif, menandai peningkatan signifikan dari pendekatan sebelumnya. Penelitian merekomendasikan perluasan dataset dan pengembangan sistem pendukung keputusan berbasis prediksi untuk meningkatkan efektivitas pemasaran dealer mobil.
Kata kunci: Machine learning; Random forest; XGBoost
References
A. G. Wicaksono and I. Nurhidayat, “Penerapan Algoritma Machine Learning untuk Prediksi Pelanggan Potensial pada Dealer Mobil,” J. Inform. Univ. Pamulang, vol. 8, no. 1, pp. 12–20, 2023, [Online]. Available: https://ojs.unpam.ac.id/index.php/informatika/article/view/11726
B. S. C. Putra, I. Tahyudin, B. A. Kusuma, and K. N. Isnaini, “Efektivitas Algoritma Random Forest, XGBoost, dan Logistic Regression dalam Prediksi Penyakit Paru-paru,” Techno.Com, vol. 23, no. 4, pp. 210–218, 2024, [Online]. Available: https://publikasi.dinus.ac.id/index.php/ technoc/article/view/11705
A. Sharma, N. Patel, and R. Gupta, “Enhancing Predictive Customer Retention Using Machine Learning Algorithms : A Comparative Study of Random Forest , XGBoost , and Neural Networks Authors :,” pp. 1–23.
“Emre Deniz ID ∗,1 and Semanur Çökekoglu Bülbül ˘.pdf.”
A. Sudrajat and B. Subekti, “Analisis Perbandingan Algoritma Random Forest dan XGBoost untuk Prediksi Churn Pelanggan,” J. Ris. Inform., vol. 2, no. 3, pp. 184–191, 2020, [Online]. Available: https://jurnal.polibatam.ac.id/index.php/juri/article/view/1757
N. M. Sari and A. Wibowo, “Perbandingan Metode Random Forest dan Support Vector Machine untuk Prediksi Keberhasilan Penjualan,” J. Ilm. Teknol. Inf. Terap., vol. 6, no. 1, pp. 20–27, 2020, [Online]. Available: https://ejournal.undip.ac.id/index.php/jtit/article/ download/31328/19016
Y. Jin, “Sales Prediction Based on Machine Learning Approach : Support Vector Machine , Xgboost and Random Forest,” vol. 88, pp. 104–109, 2024.
T. Yang, “Sales Prediction of Walmart Sales Based on OLS , Random Forest , and XGBoost Models,” vol. 49, pp. 244–249, 2023.
M. Imani and A. Beikmohammadi, “Comprehensive Analysis of Random Forest and XGBoost Performance with SMOTE , ADASYN , and GNUS Under Varying Imbalance Levels,” vol. 13, no. 2, p. 8, 2025.
W. Wang et al., “A User Purchase Behavior Prediction Method Based on XGBoost,” 2023.
B. Kriswantara and R. Sadikin, “Used Car Price Prediction with Random Forest Regressor Model,” vol. 6, no. 1, pp. 40–49, 2022, doi: 10.52362/jisicom.v6i1.752.
D. Lestari and B. Haryanto, “Evaluasi Model Machine Learning untuk Prediksi Respon Konsumen pada Kampanye Marketing,” ROY Inform., vol. 7, no. 1, pp. 58–65, 2023.
R. Yusuf and M. A. Pratama, “Implementasi Random Forest dan XGBoost dalam Prediksi Kredit Macet,” J. Teknol. dan Sist. Inf., vol. 3, no. 1, pp. 40–48, 2022.
J. M. A. S. Dachi and P. Sitompul, “Analisis Perbandingan Algoritma XGBoost dan Algoritma Random Forest Ensemble Learning pada Klasifikasi Keputusan Kredit,” J. Ris. Rumpun Mat. dan Ilmu Pengetah. Alam, vol. 2, no. 2, pp. 87–103, 2023, doi: 10.55606/jurrimipa.v2i2.1470.
A. P. Sari and E. Prasetyo, “Prediksi Customer Churn Menggunakan Algoritma XGBoost dan LightGBM,” J. Ilmu Komput. dan Sist. Inf., vol. 9, no. 2, pp. 124–132, 2021.
M. Erkamim, S. Suswadi, M. Z. Subarkah, and E. Widarti, “Komparasi Algoritme Random Forest dan XGBoosting dalam Klasifikasi Performa UMKM,” J. Sist. Inf. Bisnis, vol. 13, no. 2, pp. 127–134, 2023, [Online]. Available: https://ejournal.undip.ac.id/index.php/ jsinbis/article/view/52428
How To Cite This :
Refbacks
- There are currently no refbacks.