PREDIKSI KECELAKAAN LALU LINTAS POLANDIA DENGAN XGBOOST, CATBOOST DAN RANDOM FOREST
Article Sidebar
Read Counter : 5
Download : 4
Main Article Content
Abstract
Kecelakaan lalu lintas tetap menjadi perhatian publik yang menonjol, dipengaruhi oleh kondisi sosial-ekonomi maupun lingkungan seperti cuaca. Studi ini bertujuan untuk memprediksi jumlah kecelakaan lalu lintas di Polandia berdasarkan faktor cuaca seperti kelembapan, suhu, dan curah hujan, serta variabel sosial-ekonomi seperti kepadatan penduduk, jumlah mobil penumpang, dan kepadatan jalan beraspal. Tiga algoritma ensemble learning, yaitu XGBoost, CatBoost, dan Random Forest, digunakan untuk mengevaluasi kinerja prediksi masing-masing. Dataset dibagi menggunakan Time Series Cross Validation, dan akurasi model dievaluasi menggunakan Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), serta koefisien determinasi (R²). Hasil penelitian menunjukkan bahwa ketiga model memiliki performa yang baik, dengan Random Forest menghasilkan kinerja terbaik, diikuti oleh XGBoost dan CatBoost.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This work is licensed under a Jurnal Komunikasi Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
References
[1] WHO, “Road traffic injuries,” World Health Organization. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries
[2] M. Romadon and R. Passarella, “ANALISIS PENGARUH KONDISI CUACA DAN JALAN TERHADAP KECELAKAAN LALU LINTAS MENGGUNAKAN K-MEANS,” Dec. 2024, Accessed: Oct. 07, 2025. [Online]. Available: http://repository.unsri.ac.id/id/eprint/162335
[3] I. J. Effendi, A. N. N. Rizki, D. O. R. Rahman, and B. Fadel, “Pendekatan Descriptive Analysis Berbasis Data Untuk Mengevaluasi Kecelakaan Lalu Lintas Di Indonesia,” J. Inform. Ilmu Komput. dan Sist. Inf., vol. 2, no. 3, 2024, Accessed: Oct. 07, 2025. [Online]. Available: https://animator.uho.ac.id/index.php/journal/article/view/1241
[4] K. Zhang, S. Wang, C. Song, S. Zhang, and X. Liu, “Spatiotemporal Heterogeneity Analysis of Provincial Road Traffic Accidents and Its Influencing Factors in China,” Sustain. 2024, Vol. 16, Page 7348, vol. 16, no. 17, p. 7348, Aug. 2024, doi: 10.3390/SU16177348.
[5] A. Filapek, Ł. Faruga, and J. Baranowski, “Bayesian Modeling of Traffic Accident Rates in Poland Based on Weather Conditions,” Appl. Sci. 2025, Vol. 15, Page 7332, vol. 15, no. 13, p. 7332, Jun. 2025, doi: 10.3390/APP15137332.
[6] N. N. Pandika Pinata, I. M. Sukarsa, and N. K. Dwi Rusjayanthi, “Prediksi Kecelakaan Lalu Lintas di Bali dengan XGBoost pada Python,” J. Ilm. Merpati (Menara Penelit. Akad. Teknol. Informasi), p. 188, Oct. 2020, doi: 10.24843/JIM.2020.V08.I03.P04.
[7] B. L. Fauzan, T. Agustin, A. Musthofiah, and H. Mahmudah, “Prediksi Klasifikasi Kecelakaan Lalu Lintas di Kota Surakarta dengan Menggunakan Metode Regresi Logistik Multinomial,” Sustain. Civ. Build. Manag. Eng., vol. 1, no. 4, pp. 9–9, Aug. 2024, doi: 10.47134/SCBMEJ.V1I4.3159.
[8] L. A. (Lucky) Rakhmat, A. (Aine) Kusumawati, R. B. (Russ) Frazila, and S. (Sri) Hendarto, “Pengembangan Model Prediksi Kecelakaan Lalu Lintas Pada Jalan Tol Purbaleunyi,” J. Tek. Sipil ITB, vol. 19, no. 3, pp. 277–288, Dec. 2012, doi: 10.5614/JTS.2012.19.3.8.
[9] S. B. Prakash, M. Raj, and A. P, “EARTHQUAKE PREDICTION USING RANDOM FOREST TREE WITH XGBOOST AND CATBOOST,” I C N K A I – 2 K 2 5 Int. Lev. Conf. Nexus Knowl. Using AI IoT, Jun. 2025, Accessed: Oct. 07, 2025. [Online]. Available: https://secp.prabodhanamfoundation.org/csn/index.php/csn-secp/article/view/91
[10] S. Markovic et al., “Application of XGBoost model for in-situ water saturation determination in Canadian oil-sands by LF-NMR and density data,” Sci. Rep., vol. 12, no. 1, pp. 1–14, Dec. 2022, doi: 10.1038/S41598-022-17886-6;SUBJMETA.
[11] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785/SUPPL_FILE/KDD2016_CHEN_BOOSTING_SYSTEM_01-ACM.MP4.
[12] N. K. Dewi, U. D. Syafitri, and S. Y. Mulyadi, “PENERAPAN METODE RANDOM FOREST DALAM DRIVER ANALYSIS,” FORUM Stat. DAN KOMPUTASI, vol. 16, no. 1, pp. 35–43, 2011, Accessed: Oct. 07, 2025. [Online]. Available: https://journal.ipb.ac.id/statistika/article/view/5443
[13] M. S. Efendi, Sarwido, and A. K. Zyen, “Penerapan Algoritma Random Forest Untuk Prediksi Penjualan Dan Sistem Persediaan Produk,” Resolusi Rekayasa Tek. Inform. dan Inf., vol. 5, no. 1, pp. 12–20, Sep. 2024, doi: 10.30865/RESOLUSI.V5I1.2149.
[14] D. Aqsha, “PERBANDINGAN KINERJA ALGORITMA EXTREME GRADIENT BOOSTING DAN RANDOM FOREST UNTUK PREDIKSI HARGA RUMAH DI JABODETABEK,” J. Ilmu Komput. dan Sist. Inf., vol. 13, no. 1, Jan. 2025, doi: 10.24912/JIKSI.V13I1.32863.
[15] Yandex, “CatBoost — Yandex Technologies.” Accessed: Oct. 07, 2025. [Online]. Available: https://yandex.com/dev/catboost/
[16] A. V. Dorogush, V. Ershov, and A. Gulin, “CatBoost: gradient boosting with categorical features support,” Oct. 2018, Accessed: Oct. 07, 2025. [Online]. Available: https://arxiv.org/pdf/1810.11363
[17] J. T. Hancock and T. M. Khoshgoftaar, “CatBoost for big data: an interdisciplinary review,” J. Big Data, vol. 7, no. 1, pp. 1–45, Dec. 2020, doi: 10.1186/S40537-020-00369-8/FIGURES/9.
[18] A. Mironov and I. Khuziev, “Optimization of Oblivious Decision Tree Ensembles Evaluation for CPU,” Nov. 2022, Accessed: Oct. 07, 2025. [Online]. Available: https://arxiv.org/pdf/2211.00391
[19] W. Kainz, M. A. Brovelli, D. Wang, and H. Qian, “CatBoost-Based Automatic Classification Study of River Network,” ISPRS Int. J. Geo-Information 2023, Vol. 12, Page 416, vol. 12, no. 10, p. 416, Oct. 2023, doi: 10.3390/IJGI12100416.
[20] S. Geeitha, K. Ravishankar, J. Cho, and S. V. Easwaramoorthy, “Integrating cat boost algorithm with triangulating feature importance to predict survival outcome in recurrent cervical cancer,” Sci. Rep., vol. 14, no. 1, pp. 1–19, Dec. 2024, doi: 10.1038/S41598-024-67562-0;SUBJMETA.
[21] M. E. Haque et al., “StackLiverNet: A Novel Stacked Ensemble Model for Accurate and Interpretable Liver Disease Detection,” Jul. 2025, Accessed: Oct. 07, 2025. [Online]. Available: https://arxiv.org/pdf/2508.00117
[22] L. Benedict, “Prediksi Tingkat Kematian Covid-19 di Indonesia dengan menggunakan Metode Linear Regression,” 2022.
[23] R. Ritonga, M. Ibnu Rasyid, J. Angga Putra, and M. Masrizal, Optimalisasi Kinerja Pegawai Pertanian (Studi Kasus Penggunaan Algoritma Regresi Linear). Literasi Nusantara, 2024. Accessed: Oct. 07, 2025. [Online]. Available: https://penerbitlitnus.co.id/portfolio/optimalisasi-kinerja-pegawai-pertanian/
[24] Ł. Faruga, A. Filapek, M. Kraszewska, and J. Baranowski, “Dataset for Traffic Accident Analysis in Poland: Integrating Weather Data and Sociodemographic Factors,” Appl. Sci. 2025, Vol. 15, Page 7362, vol. 15, no. 13, p. 7362, Jun. 2025, doi: 10.3390/APP15137362.