Pendekatan Model Machine Learning dalam Pemeringkatan Status Sosial Ekonomi Rumah Tangga di Indonesia

Metode yang digunakan untuk pemeringkatan status sosial ekonomi rumah tangga Basis Data Terpadu adalah dengan memprediksi nilai pengeluaran rumah tangga dengan metode Proxy Mean Testing (PMT). Secara umum metode ini merupakan model prediksi dengan menggunakan teknik regresi. Pilihan model statistik yang digunakan adalah forward-stepwise. Dalam praktiknya diasumsikan bahwa variabel prediktor yang digunakan dalam PMT memiliki korelasi linier dengan variabel pengeluaran. Penelitian ini mencoba menerapkan pendekatan machine learning sebagai alternatif metode prediksi selain model forward-stepwise. Model dibangun menggunakan beberapa algoritma machine learning seperti Multivariate Adaptive Regression Splines (MARS), K-Nearest Neighbors, Decision Tree, dan Bagging. Hasil pemodelan menunjukkan bahwa model machine learning menghasilkan nilai rata-rata inclusion error (IE) lebih rendah dibandingkan nilai rata-rata exclusion error (EE). Model machine learning bekerja efektif dalam mengurangi IE namun belum cukup sensitif dalam mengurangi EE. Nilai rata-rata IE model machine learning sebesar 0,21 sedangkan nilai rata-rata IE model PMT sebesar 0,29.

Download Full-text

Machine Learning Predictive Models for Pile Drivability: An Evaluation of Random Forest Regression and Multivariate Adaptive Regression Splines

Information Technology in Geo-Engineering - Springer Series in Geomechanics and Geoengineering ◽

10.1007/978-3-030-32029-4_21 ◽

2019 ◽

pp. 243-255

Author(s):

Wengang Zhang ◽

Chongzhi Wu

Keyword(s):

Machine Learning ◽

Random Forest ◽

Predictive Models ◽

Multivariate Adaptive Regression Splines ◽

Regression Splines ◽

Random Forest Regression ◽

Adaptive Regression ◽

Adaptive Regression Splines

Download Full-text

Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds

Hydrology and Earth System Sciences ◽

10.5194/hess-20-2611-2016 ◽

2016 ◽

Vol 20 (7) ◽

pp. 2611-2628 ◽

Cited By ~ 70

Author(s):

Julie E. Shortridge ◽

Seth D. Guikema ◽

Benjamin F. Zaitchik

Keyword(s):

Machine Learning ◽

Predictive Accuracy ◽

Generalized Additive Models ◽

Additive Models ◽

Multivariate Adaptive Regression Splines ◽

Regression Splines ◽

Climate Conditions ◽

Machine Learning Methods ◽

Adaptive Regression ◽

Adaptive Regression Splines

Abstract. In the past decade, machine learning methods for empirical rainfall–runoff modeling have seen extensive development and been proposed as a useful complement to physical hydrologic models, particularly in basins where data to support process-based models are limited. However, the majority of research has focused on a small number of methods, such as artificial neural networks, despite the development of multiple other approaches for non-parametric regression in recent years. Furthermore, this work has often evaluated model performance based on predictive accuracy alone, while not considering broader objectives, such as model interpretability and uncertainty, that are important if such methods are to be used for planning and management decisions. In this paper, we use multiple regression and machine learning approaches (including generalized additive models, multivariate adaptive regression splines, artificial neural networks, random forests, and M5 cubist models) to simulate monthly streamflow in five highly seasonal rivers in the highlands of Ethiopia and compare their performance in terms of predictive accuracy, error structure and bias, model interpretability, and uncertainty when faced with extreme climate conditions. While the relative predictive performance of models differed across basins, data-driven approaches were able to achieve reduced errors when compared to physical models developed for the region. Methods such as random forests and generalized additive models may have advantages in terms of visualization and interpretation of model structure, which can be useful in providing insights into physical watershed function. However, the uncertainty associated with model predictions under extreme climate conditions should be carefully evaluated, since certain models (especially generalized additive models and multivariate adaptive regression splines) become highly variable when faced with high temperatures.

Download Full-text