Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Inferensi MATHunesa: Jurnal Ilmiah Matematika
Khusnia Nurul Khikmah
Universitas Palangka Raya
Computer Science & IT Decision Sciences, Operations Research & Management Engineering Mathematics Social Sciences

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
ESG Factors and Interest Rate Stability: A Comparative Analysis of Statistical and Machine Learning Approaches Khusnia Nurul Khikmah; A'yunin Sofro
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9511

Abstract

This study aims to compare the performance of basic statistical approaches and machine learning in identifying environmental, social, and governance (ESG) issues that influence the stability of the rupiah through the Indonesian interest Rate. This study proposes two approaches: machine learning analysis (long short-term memory (LSTM) and multiple long short-term memory (M-LSTM)) and fundamental statistical models (autoregressive integrated moving average (ARIMA), transfer function, and Koyck regression) to forecast the Indonesian interest rate time series data based on ESG factors. The analysis uses a completely randomized design to capture complex patterns, utilizing interest rate data, PM2.5 air quality data, and rainfall index data. This study provides novelty through data splitting scenarios in its empirical analysis and a comparative study of approaches to the model. The analysis results indicate that ESG factors, specifically air quality (PM2.5) and the rainfall index, have a significant influence on Indonesian interest rate values, as determined by the transfer function results, Koyck regression, and M-LSTM model analyses. All proposed model approaches demonstrate good forecasting accuracy, empirically proven by MAPE values with MAPE<10%. The MAPE values of the basic statistical models (Koyck regression, transfer function, and ARIMA) are 0.2842%, 1.0350%, and 2.1245%, outperforming machine learning models (LSTM and M-LSTM) with MAPE values of 4.660% and 7.7353%.
EVALUASI KINERJA PENANGANAN DATA TIDAK SEIMBANG DALAM MEMPREDIKSI LAJU PERTUMBUHAN PENDUDUK DI KALIMANTAN Khusnia Nurul Khikmah; A'yunin Sofro
MATHunesa: Jurnal Ilmiah Matematika Vol. 13 No. 3 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/mathunesa.v13n3.p332-341

Abstract

Laju pertumbuhan penduduk merupakan indikator demografi krusial yang memengaruhi berbagai aspek kabupaten dan kota di Kalimantan, sehingga membutuhkan analisis komprehensif dalam memodelkan data. Fakta lapangannya masalah ini salah satunya dipengaruhi oleh fenomena ketidakseimbangan data atau satu kategori laju pertumbuhan penduduk lebih dominan. Oleh karena itu, penelitian ini mengusulkan kajian perbandingan metode penanganan data tidak seimbang dengan model analisis regresi logistik. Empat metode penanganan data tidak seimbang ini adalah tanpa penanganan atau baseline, kedua dengan metode random over sampling (ROS), random undersampling (RUS), dan synthetic minority oversampling technique (SMOTE). Dimana data yang digunakan adalah data sekunder yang diambil dari Badan Pusat Statistik (BPS) lima provinsi di Kalimantan. Hasil analisis laju pertumbuhan penduduk kabupaten dan kota di Kalimantan menunjukkan bahwa model regresi logistic biner dengan tanpa penanganan atau baseline memberikan akurasi hasil prediksi terbaik. Berdasarkan nilai akurasi, balanced accuracy, dan ROC menunjukkan nilai tertinggi dibandingkan metode penanganan data tidak seimbang lainnya, yaitu untuk data latih sebesar 66.7%, 53.1%, dan 76.51%. Sedangkan untuk data uji sebesar 72.7%, 62.5%, dan 82.14%.
Co-Authors A&#039;yunin Sofro A'yunin Sofro