Exploration PSO Model for Poverty Prediction: An Empirical Study of Socio-Economic Data

Lilis Suriani, Syaharuddin Syaharuddin, Vera Mandailina

Abstract


This study aims to evaluate the effectiveness of the Particle Swarm Optimization (PSO) method in predicting the percentage of poor people in Indonesia. This method was chosen because of its ability to solve non-linear prediction problems efficiently. The data used is annual secondary data from the Central Bureau of Statistics (BPS) for the period 2015-2024. The PSO model was developed with certain parameters, and the prediction process was carried out for the period 2025-2029. The prediction results show a gradual increase in the number of poor people, indicating a potential slowdown in poverty reduction. Evaluation of model accuracy using the Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) indicators resulted in values of 1.66% and 0.773%, respectively. These values reflect a very low level of prediction error and indicate that the PSO model has a reliable performance. Therefore, the PSO method is considered effective and reliable as a decision-making tool in data-based socioeconomic policy planning.


Keywords


Poverty Prediction Particle Swarm Optimization (PSO), Socio-Economic, Data.

Full Text:

PDF

References


Amaliah, D. (2015). Pengaruh Partisipasi Pendidikan Terhadap Persentase Penduduk Miskin. Faktor Jurnal Ilmiah Kependidikan, 2(3), 231–239.

Asadi, A., Wang, Q., & Mancuso, V. (2014). A survey on device-to-device communication in cellular networks. IEEE Communications Surveys and Tutorials, 16(4), 1801–1819. https://doi.org/10.1109/COMST.2014.2319555

Badrul, M., & Id, M. M. A. (2017). Optimasi Algoritma Neural Network Dengan Algoritma Genetika Dan Particle Swarm Optimization Untuk Memprediksi Hasil Pemilukada. Pilar Nusa Mandiri, 13(1), 1–11.

Fardhani, A. A., Simanjuntak, D. I. N., & Wanto, A. (2018). Prediksi Harga Eceran Beras Di Pasar Tradisional Di 33 Kota Di Indonesia Menggunakan Algoritma Backpropagation. Jurnal Infomedia, 3(1). https://doi.org/10.30811/jim.v3i1.625

Head, B. W. (2010). Reconsidering evidence-based policy: Key issues and challenges. Policy and Society, 29(2), 77–94. https://doi.org/10.1016/j.polsoc.2010.03.001

Ilmi, R. R., Mahmudy, W. F., & Ratnawati, D. E. (2015). Optimasi Penjadwalan Perawat Menggunakan Algoritma Genetika. Jurnal Mahasiswa PTIIK Universitas Brawijaya, 5(13), 8.

Indahyanti, U., Azizah, N. L., & Setiawan, H. (2022). Pendekatan Ensemble Learning Untuk Meningkatkan Akurasi Prediksi Kinerja Akademik Mahasiswa. Jurnal Sains Dan Informatika, 8(2), 160–169. https://doi.org/10.34128/jsi.v8i2.459

Jesen, J., Purba, T. S. M., & ... (2024). Prediksi Probabilitas Tren Penurunan Jumlah Penduduk Miskin di Indonesia. … Literacy Innovation and …, 02, 19–25. https://ejurnal.yarukom.com/index.php/SinoviTech/article/download/11/15

Nuraeni, Y. (2018). Dampak Perkembangan Industri Pertambangan Nikel. Seminar Nasional Edusaintek, 12–22.

Perwira Negara, H. R. (2020). Computational Modeling of ARIMA-based G-MFS Methods: Long-term Forecasting of Increasing Population. International Journal of Emerging Trends in Engineering Research, 8(7), 3665–3669. https://doi.org/10.30534/ijeter/2020/126872020


Refbacks

  • There are currently no refbacks.