A Comparison Of Adam And Nelder–Mead Simplex Optimization In Neural Network-Based Relative Poverty Classification
Keywords: Adam, Nelder-Mead simplex, neural network, optimization, poverty
Abstract
Statistical optimization plays an important role in improving the performance of neural network (NN) models by optimizing their weights and biases. This study compares the performance of the Adaptive Moment Estimation (Adam) and Nelder-Mead (NM) simplex optimization methods for neural network-based relative poverty classification in Indonesia. Secondary data from Statistics Indonesia (BPS) in 2023 covering 514 regencies/cities, nine explanatory variables, and one binary response variable representing relatively high-poverty and relatively low-poverty areas were analyzed. The analysis included data preprocessing, exploratory data analysis, NN model development, hyperparameter tuning, and performance evaluation using the area under the receiver operating characteristic curve (AUC), accuracy, precision, sensitivity, specificity, and F1-score. The Adam model consistently outperformed the NM simplex model across almost all evaluation metrics, achieving an AUC of 0.818 compared with 0.735. Adam also obtained higher accuracy (0.777 vs. 0.738), precision (0.771 vs. 0.692), specificity (0.869 vs. 0.803), and F1-score (0.701 vs. 0.667), while both models achieved the same sensitivity (0.643). These findings demonstrate that Adam provides a more effective and computationally efficient optimization approach than the NM simplex for neural network-based relative regional poverty classification in Indonesia.
Downloads
References
Aggarwal, S. (2023). LSTM based anomaly detection in time series for United States exports and imports. Munich Personal RePEc Archive, (117149).
Agustin, M., & Prahasto, T. (2012). Penggunaan jaringan syaraf tiruan backpropagation untuk seleksi penerimaan mahasiswa baru pada jurusan Teknik Komputer di Politeknik Negeri Sriwijaya. Jurnal Sistem Informasi Bisnis, 2, 89–97. https://doi.org/10.21456/vol2iss2pp089-097
Alkhairi, P., & Windarto, A. P. (2023). Classification analysis of back propagation-optimized CNN performance in image processing. Journal of Systems Engineering and Information Technology (JOSEIT), 2(1), 8–15. https://doi.org/10.29207/joseit.v2i1.5015
Allo, R. F. A. R., & Fevriera, S. (2025). Efek kuantitas dan kualitas manusia terhadap kemiskinan di Kaltara. Jurnal Ekonomika, 16(1), 1–17. https://doi.org/10.35334/sdr9y076
Allorerung, P. P., Erna, A., Bagussahrir, M., & Alam, S. (2024). Analisis performa normalisasi data untuk klasifikasi k-nearest neighbor pada dataset penyakit. Jurnal Informatika Sunan Kalijaga, 9(3), 178–191. https://doi.org/10.14421/jiska.2024.9.3.178-191
Apriza, I., Izza, M. F., Sebastian, M. N., & Paduloh, P. (2025). Optimasi produksi konveksi IZZA Collection antara dua desain t-shirt menggunakan metode programa linear dan diselesaikan dengan metode simplex. HUMANITIS: Jurnal Humaniora, Sosial, Dan Bisnis, 3(1), 194–200.
Attwood, K., Tian, L., & Xiong, C. (2014). Diagnostic thresholds with three ordinal groups. Journal of Biopharmaceutical Statistics, 24(3), 608–633. https://doi.org/10.1080/10543406.2014.888437
Bantis, L. E., Nakas, C. T., & Reiser, B. (2019). Construction of confidence intervals for the maximum of the Youden index and the corresponding cutoff point of a continuous biomarker. Biometrical Journal, 61, 138–156. https://doi.org/10.1002/bimj.201700107
Baudin, M. (2010). Nelder-mead user’s manual. Consortium Scilab – DIGITEO.
Bishop, C. M. (2006). Pattern recognition and machine learning (M. Jordan, J. Kleinberg, & B. Scholkopf, Eds.). Springer.
BPS Kabupaten Enrekang. (2024). Indeks pembangunan manusia tahun 2024 Kabupaten Enrekang (Vol. 9). BPS Kabupaten Enrekang.
Cerdà, V., Cerdà, J. L., & Idris, A. M. (2015). Optimization using the gradient and simplex methods. Talanta, 148, 641–648. https://doi.org/10.1016/j.talanta.2015.05.061
Dantzig, G. B., Orden, A., & Wolfe, P. (1955). The generalized simplex method for minimizing a linear form under linear inequality restraints. Pacific Journal of Mathematics, 5(2), 183–195. https://doi.org/10.2140/pjm.1955.5.183
Faritz, M. N., & Soejoto, A. (2020). Pengaruh pertumbuhan ekonomi dan rata-rata lama sekolah terhadap kemiskinan di Provinsi Jawa Tengah. JUPE (Jurnal Pendidikan Ekonomi), 8(1), 16–21. https://doi.org/10.26740/jupe.v8n1.p15-21
Goodfellow, I., Bengio, Y., & Courvile Aaron. (2016). Deep learning. In Healthcare Informatics Research (Number 4). The MIT Press.
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. 3rd International Conference on Learning Representations, 1–15. http://arxiv.org/abs/1412.6980
Kolda, T. G., Lewis, R. M., & Torczon, V. (2003). Optimization by direct search: New perspectives on some classical and modern methods. Society for Industrial and Applied Mathematics, 45(3), 385–482. https://doi.org/10.1137/S003614450242889
Kurniati, I., Winarno, H., & Yuliyanti, D. (2023). Pemanfaatan algoritma neural network untuk predictive analytic angka buta huruf di Indonesia. Jurnal Elekto & Informatika Swadharma (JEIS), 3(2), 94–104. https://doi.org/10.56486/jeis.vol3no2.364
Li, J. (2024). Area under the ROC Curve has the most consistent evaluation for binary classification. Plos One, 1–28. https://doi.org/10.1371/journal.pone.0316019
Mohtasham, F., Nazari, S. S. H., Pourhoseingholi, M. A., Kavousi, K., & Zali, M. R. (2026). Hybrid feature-selection and diversity-guided stacking framework for interpretable ensemble learning: Application to COVID-19 mortality prediction. Plos One, 21(4). https://doi.org/10.1371/journal.pone.0341198
Nelder, J. A., & Mead, R. (1965). A simplex method for function minimization. The Computer Journal, 7, 308–312. https://doi.org/10.1093/comjnl/7.4.308
Ozaki, Y., Yano, M., & Onishi, M. (2017). Effective hyperparameter optimization using Nelder-Mead method in deep learning. IPSJ Transactions on Computer Vision and Applications, 9(20), 1–12. https://doi.org/10.1186/s41074-017-0030-7
Prasetyawan, P., Ahmad, I., Borman, R. I., Ardiansyah, A., Pahlvei, Y. A., & Kurniawan, D. E. (2018, October 4). Classification of the period undergraduate study using back-propagation neural network. International Conference on Applied Engineering (ICAE).
Prasetyo, V. R., Mercifia, M., Averina, A., Sunyoto, L., & Budiarjo, B. (2022). Prediksi rating film pada website IMDB menggunakan metode neural network. Network Engineering Research Operation (NERO), 7(1), 1–8. http://repository.ubaya.ac.id/id/eprint/41805
Rainio, O., Teuho, J., & Klén, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 14(6086). https://doi.org/10.1038/s41598-024-56706-x
Reddi, S. J., Kale, S., & Kumar, S. (2018). On the convergence of ADAM and beyond. International Conference on Learning Representations, 1–23. https://doi.org/10.48550/arXiv.1904.09237
Sakti, A. I., Saputra, L., Suhendra, H., Halim, N., Alviari, I., Ilham, M. R. N., Putri, M. H. N., & Dalimunthe, D. Y. (2024). Implementasi artificial neural network (ANN) dalam memprediksi nilai tukar rupiah terhadap dolar Amerika. Euler : Jurnal Ilmiah Matematika, Sains Dan Teknologi, 12(2), 124–130. https://doi.org/10.37905/euler.v12i2.26654
Saputri, A. A. (2023). Implementasi algoritma backpropagation, LVQ, dan multilayer perceptron untuk klasifikasi tingkat kemiskinan Kabupaten/Kota di Indonesia [Skripsi]. Universitas Hamzanwadi.
Saragih, T. H., & Huda, N. (2022). Jaringan syaraf tiruan backpropagation dengan adaptive moment estimation untuk klasifikasi penyakit Covid-19 di Kalimantan Selatan. Epsilon: Jurnal Matematika Murni Dan Terapan, 16, 162–172.
Si, T., He, F., Li, P., & Gao, X. (2023). Tri-modality consistency optimization with heterogeneous augmented images for visible-infrared person re-identification. Neurocomputing, 523, 170–181. https://doi.org/10.1016/j.neucom.2022.12.042
Silva, K. G.-E., Aloise, D., Souza, S. X.-D., & Mladenovic, N. (2018). Less is more: Simplified nelder-mead method for large unconstrained optimization. Yugoslav Journal of Operations Research, 28(2), 153–169. https://doi.org/10.2298/YJOR180120014G
Suhendra, C. D., & Saputra, A. C. (2020). Penentuan parameter learning rate selama pembelajaran jaringan syaraf tiruan backpropagation menggunakan algoritma genetika. Jurnal Teknologi Informasi, 4(2), 202–212. https://doi.org/10.47111/jti.v14i2.1141
Suhendra, C. D., & Wardoyo, R. (2015). Penentuan arsitektur jaringan syaraf tiruan backpropagation (bobot awal dan bias awal) menggunakan algoritma genetika. Indonesian Journal of Computing and Cybernetics Systems, 9(1), 77–88.
Szandala, T. (2020). Review and comparison of commonly used activation functions for deep neural networks. Bio-Inspired Neurocomputing, 203–224. https://doi.org/10.1007/978-981-15-5495-7_11
Windarto, A. P. (2017). Implementasi JST dalam menentukan kelayakan nasabah pinjaman kur pada Bank Mandiri mikro serbelawan dengan metode backpropagation. Jurnal Sains Komputer & Informatika (J-SAKTI, 1(1), 12–32. http://ejurnal.tunasbangsa.ac.id/index.php/jsakti
Wulandari, G., Febriyanti, N. A., Anwar, K., & Matematika, F. (2022). Pemodelan persentase penduduk miskin di Indonesia menggunakan regresi probit dan regresi logistik. Prosiding Seminar Nasional Matematika, Statistika, Dan Aplikasinya, 354–368.
Copyright (c) 2026 Nabil Bintang Prayoga, Rose Dwi Aulia Amaradhani, Vito Raditya Pratama, Raihan Sabillah Adisecha, Fathiyya Mufida, Akbar Rizki
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.