Predicting Poverty Severity Index Values With Demographic Features Of Indonesian City Districts Using Regression Models

Chaerunisa, Shafina (2024) Predicting Poverty Severity Index Values With Demographic Features Of Indonesian City Districts Using Regression Models. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 5025201129-Undergraduate_Thesis.pdf] Text
5025201129-Undergraduate_Thesis.pdf
Restricted to Repository staff only until 1 October 2026.

Download (5MB) | Request a copy

Abstract

Kemiskinan merupakan salah satu penyebab kematian terbanyak di dunia. Jumlah penduduk miskin yang terus bertambah dari tahun ke tahun menjadi masalah utama di Indonesia. Kemiskinan menjadi tantangan tersendiri dalam hal identifikasi kemiskinan karena faktor geografis, sosial, ekonomi, pertanian, pertambangan, dan berbagai faktor lainnya yang beragam. Setiap daerah atau wilayah memiliki tingkat keparahan kemiskinan yang berbeda-beda, baik yang meningkat maupun yang menurun. Oleh karena itu, untuk mencegah dan mengurangi masalah tersebut, diperlukan metode untuk memprediksi tingkat keparahan kemiskinan dan membantu pertumbuhan ekonomi daerah di Indonesia agar dapat mengidentifikasi penyebabnya. Dalam makalah ini, diusulkan sebuah model untuk memprediksi indeks keparahan kemiskinan dengan pendekatan regresi menggunakan variabel-variabel, termasuk demografi sosial dan ekonomi kabupaten dan kota. Prosedur yang dilakukan meliputi pengumpulan data, praproses data, pemodelan, serta penilaian dan analisis hasil. Pengumpulan data meliputi pengumpulan informasi demografi dari setiap kabupaten kota dari tahun 2014 hingga 2022. Perbandingan model machine learning, yaitu Random Forest, XGBoost, TabNet, dan lainnya dilakukan untuk mendapatkan hasil prediksi. Hasil prediksi yang diperoleh dievaluasi dengan evaluasi metrik regresi dan menghasilkan Random Forest sebagai hasil terbaik dengan akurasi 69%
======================================================================================================================================
Poverty is one of the leading causes of death in the world. The number of people living in poverty is increasing year by year, which is a major problem in Indonesia. Poverty poses a challenge in terms of identification owing to the diverse geographical, social, economy, agricultural, mining, and various other factors. Each region or area exhibits a distinct level of poverty severity, which may either be on the rise or declining. Thus, to prevent and reduce this problem, method is needed to predict the level of poverty severity and helps the economic growth of Indonesia’s area to be able to identify what the causes. In this paper, a model is proposed to predict the poverty severity index with a regression approach using variables, including social and economic demographics of districts and cities. The procedure includes data collection, data preprocessing, modelling, and result assessment and analysis. Data collection includes collecting demographic information from each city district from 2014 to 2022. Comparison of machine learning models, namely, Random Forest, XGBoost, TabNet, and others were carried out to obtain prediction results. The prediction results obtained were evaluated by regression metrics evaluation and resulted in Random Forest as the best result with 69% accuracy.

Item Type: Thesis (Other)
Uncontrolled Keywords: Economy, Education, Index, Poverty, Regression, Ekonomi, Indeks, Kemiskinan, Pendidikan, Regresi
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User: Shafina Chaerunisa
Date Deposited: 01 Aug 2024 01:57
Last Modified: 09 Sep 2024 08:59
URI: http://repository.its.ac.id/id/eprint/110058

Actions (login required)

View Item View Item