Jurnal Algoritma, Logika dan Komputasi

Gradient Boosting is a machine learning algorithm that combines several simple parameter functions that aim to predict a fairly accurate information from existing data. In contrast to statistical methods in general, this Gradient boosting provides interpretable information, while requiring little data preprocessing and tuning of parameters. Boosting Gradient can be applied to classify or regress data, complex interaction is modeled simply and minimizes loss of information while in predictor management, so this algorithm is good enough to be used for modeling the cost of insurance loss. This paper presents the GB theory and its application to the problem of predicting '' at-fault '' accidents on auto loss costs using data from Canadian insurance companies. The predictive accuracy of the model is compared to the conventional Generalized Linear Model (GLM) approach.Gradient Boosting is a machine learning algorithm that combines several simple parameter functions that aim to predict a fairly accurate information from existing data. In contrast to statistical methods in general, this Gradient boosting provides interpretable information, while requiring little data preprocessing and tuning of parameters. Boosting Gradient can be applied to classify or regress data, complex interaction is modeled simply and minimizes loss of information while in predictor management, so this algorithm is good enough to be used for modeling the cost of insurance loss. This paper presents the GB theory and its application to the problem of predicting '' at-fault '' accidents on auto loss costs using data from Canadian insurance companies. The predictive accuracy of the model is compared to the conventional Generalized Linear Model (GLM) approach.

Gradient Boosting, Generalized Linear Model, Cost of insurance loss

McCullagh, P., & Nelder, J. (1989).Generalized linear models(2nd ed.). Chapman and Hall.

Anderson, D., Feldblum, S., Modlin, C., Schirmacher, D. Schirmacher, E., & Thandi, N.(2007). A practitioner’s guide to generalized linear models. Casualty Actuarial Society (CAS), Syllabus Year: 2010, Exam Number: 9, 1–116.

Haberman, S., & Renshaw, A. (1996). Generalized linear models and actuarial science. Journal of the Royal Statistical Society, Series D, 45, 407–436.

J. A. Ginting, “Data Mining Untuk Analisa Pengajuan Kredit Dengan Menggunakan Metode Logistik Regresi,” J. Algoritm. Log. dan Komputasi, vol. 2, no. 2, pp. 164–169, 2019, doi: 10.30813/j-alu.v2i2.1845.

B. Hakim, “Analisa Sentimen Data Text Preprocessing Pada Data Mining Dengan Menggunakan Machine Learning,” JBASE - J. Bus. Audit Inf. Syst., vol. 4, no. 2, pp. 16–22, 2021, doi: 10.30813/jbase.v4i2.3000.

Brieman, L., Friedman, J., Olshen, R., & Stone, C. (1984).Classification and regression trees. CRC Press.

Schapire, R. (1990). The strength of weak learnability. Machine Learning, 5, 197–227.

Freund, Y., & Schapire, R. (1996). Experiments with a new boosting algorithm. Proceedings of the International Conference on Machine Learning, 13(pp. 148–156).

Friedman, J., Hastie, T., & Tibshirani, R. (2000). Additive logistic regression: A statistical view of boosting.The Annals of Statistics, 28, 337–407.

C. Herdian, A. Kamila, and I. G. Agung Musa Budidarma, “Studi Kasus Feature Engineering Untuk Data Teks: Perbandingan Label Encoding dan One-Hot Encoding Pada Metode Linear Regresi,” Technol. J. Ilm., vol. 15, no. 1, p. 93, 2024, doi: 10.31602/tji.v15i1.13457.

Friedman, J. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29, 1189–1232.

Brieman, L. (2001). Statistical modeling: The two cultures.Statistical Science, 16,199–231.

Francis, L. (2001). Neural networks demystified. Casualty Actuarial Society Forum, Winter, 2001, 252–319.

Wikipedia. 2018. Gradient Boosting. Diakses pada 23 Mei 2018, dari https://en.wikipedia.org/wiki/Gradient_boosting