Claim Missing Document
Check
Articles

Pemodelan Indeks Pembangunan Manusia di Kalimantan Timur Menggunakan Spasial Durbin Data Panel Kaerudin, Nandira Putri; Gusriani, Nurul; Ruchjana, Budi Nurani
Jurnal Matematika Integratif Vol 20, No 1: April 2024
Publisher : Department of Matematics, Universitas Padjadjaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24198/jmi.v20.n1.55158.101-115

Abstract

Indeks Pembangunan Manusia (IPM) merupakan salah satu indikator yang dapat digunakan untuk mengukur kemajuan suatu negara. Di Indonesia sendiri masih terdapat ketimpangan IPM antar provinsinya. Provinsi Kalimantan Timur merupakan salah satu provinsi yang memiliki rata-rata IPM tinggi di Indonesia, sehingga perlu dilakukan studi mengenai IPM untuk memberikan gambaran bagi provinsi dengan IPM rendah. IPM di suatu wilayah dipengaruhi oleh wilayah sekitarnya, hal ini disebabkan oleh efek spasial. Analisis regresi spasial merupakan metode yang mampu mengakomodasi efek spasial. Spatial Durbin Model (SDM) adalah salah satu pengembangannya. Selain itu, penggunaan data panel pada model menyebabkan variabilitas pada data. Penelitian ini bertujuan untuk memodelkan IPM di Kalimantan Timur menggunakan spasial durbin data panel meliputi lima kategori: Persentase penduduk miskin; Tingkat Partisipasi Angkatan Kerja (TPAK); Persentase penduduk; Angka Partisipasi Murni (APM); Persentase rumah tangga menurut fasilitas toilet sendiri. Berdasarkan hasil uji Hausman dan Chow, terdapat efek tetap pada setiap kabupaten/kota sehingga FEM merupakan jenis data panel yang digunakan. Selain itu, Hasil uji Moran’s I mengindikasikan adanya dependensi spasial positif dalam data IPM. Koefisien determinasi pada model spasial Durbin data panel menunjukkan nilai 99,92417% yang berarti model ini baik digunakan untuk memodelkan IPM di Kalimantan Timur.
Estimation of Labor Force Participation Rate (TPAK) in Java's Data-Scarce Areas Using Ordinary Cokriging Angelina, Sofia; Gusriani, Nurul; Firdaniza, Firdaniza
Jurnal Matematika Integratif Vol 21, No 2: Oktober 2025
Publisher : Department of Matematics, Universitas Padjadjaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24198/jmi.v21.n2.65239.229-244

Abstract

The quality of the labor force is crucial for economic development, and the Labor Force Participation Rate (TPAK) is a key employment indicator. In 2024, TPAK data collection in Java Island faced gaps in DKI Jakarta and Banten Provinces, limiting comprehensive labor mapping. To overcome this, spatial estimation methods are needed using data from surrounding areas and auxiliary variables. The Open Unemployment Rate (TPT) has a strong inverse relationship with TPAK, each 1\% TPAK increase lowers TPT by 14,82\%, making it a suitable auxiliary variable. This study estimates the 2024 TPAK for DKI Jakarta and Banten using the ordinary cokriging method, with TPT as the secondary variable. Spatial autocorrelation analysis confirmed that TPAK and TPT exhibit spatial patterns, are normally distributed, and meet stationarity assumptions. The best cross semivariogram model was identified using k-fold cross validation, which selected the spherical model with the lowest average RMSE of 4,24. The resulting ordinary cokriging model accurately predicted TPAK values, achieving a MAPE of 3,25\%. These estimates enable spatial visualization of TPAK in previously unobserved areas, contributing to a more complete understanding of labor participation across Java Island.
Struktur Aljabar untuk Barisan Kodon dari Asam Deoksiribonukleat (DNA) Hasan, Nabila Nurmala; Kurniadi, Edi; Gusriani, Nurul
Jurnal Matematika Integratif Vol 21, No 2: Oktober 2025
Publisher : Department of Matematics, Universitas Padjadjaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24198/jmi.v21.n2.67778.213-228

Abstract

This article discusses the algebraic structure of codon sequences as a representation of DNA nitrogen base sets in mathematical terms. The study aims to prove what algebraic structures are obtained for codon sequences from DNA bases. The methods used include qualitative research methods in the form of literature studies and quantitative research methods in the form of experiments on DNA base sets. In mathematical notation, the nitrogen bases of DNA can be collected in a set and connected into algebraic structures through a bijective mapping on the Galois field of order 4. This results in the set B being viewed as a Galois field of order 4. Additionally, DNA base triplets or codons can be represented in mathematical form. Furthermore, these codons are bijectively mapped onto the Galois field of order 64, so that the resulting algebraic structure is a field. The result of this study show that the codon sequences have an algebraic structure in the form of a one-dimensional vector space over the Galois field on the codon. For further research, the Lie structure in codon can be investigated through the construction of its Lie brackets, where this vector space is a necessary condition for Lie algebras.
Clustering of Banking Sector Stocks using Integration of Fourier Transform, Spectral Clustering, and Fuzzy C-Means as a Basis for Mean-Variance Portfolio Optimization Ricardo, Dimitri Salsabila Fakhriyah; Gusriani, Nurul; Napitupulu, Herlina
Jurnal Matematika Integratif Vol 22, No 1: April 2026
Publisher : Department of Matematics, Universitas Padjadjaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24198/jmi.v22.n1.69287.59-72

Abstract

The Indonesian capital market has experienced significant growth accompanied by high volatility, particularly in the banking sector whichholds a substantial contribution to market capitalization. Extremevolatility during the 2019-2024 period triggered by the impact of theCOVID-19 pandemic, economic recovery phases, and global macroeconomic challenges has created complexities in investment decisionmaking and portfolio optimization, which often produces unstable solutions under uncertain market conditions. Various studies have applied frequency domain analysis to uncover hidden patterns in stockprice movements or clustering to group stocks based on their characteristics to support optimal investment decision-making, however theintegration of these two approaches remains limited in its application togenerate robust portfolio optimization solutions in the Indonesian capital market. This study aims to generate clustering of banking sectorstocks through the integration of Fourier Transform, spectral clustering, and Fuzzy C-Means and to construct an optimal portfolio using theMean-Variance method based on the clustering results. This study usesclosing price data of 41 banking sector stocks on the Indonesia StockExchange for the 2019-2024 period through an integrated approach ofFourier Transform to extract frequency patterns, spectral clustering asa basis for grouping, Fuzzy C-Means to generate cluster membership degrees, and Mean-Variance for portfolio optimization. The results showthat the integration of these methods produces four optimal stock clusters consisting of nine stocks with a medium risk-low return profile,six stocks with a high risk-high return profile, fifteen stocks with a lowrisk-low return profile, and eleven stocks with a medium risk-high return profile. Based on the clustering results, four representative stockswere selected from each cluster for portfolio optimization, resulting inan optimal portfolio at a risk aversion value of ρ = 6.83 with a portfolio ratio of 3.4128877. This optimal portfolio is constructed from fourrepresentative stocks with weight allocations of 11.48% BMAS, 11.76%ARTO, 72.08% BNGA, and 4.68% BBHI, with an expected return valueof 0.0263613 and a portfolio variance of 0.0077241.
Optimal Portfolio Weight Construction Based on Arbitrage Pricing Theory (APT) and Genetic Algorithm (GA) for LQ45 Stocks in the Basic Materials Sector in 2025 Timothy Hendrawan; Nurul Gusriani; Riaman
International Journal of Business, Economics, and Social Development Vol. 7 No. 3 (2026): International Journal of Business, Economics, and Social Development (IJBESD)
Publisher : Rescollacom (Research Collaborations Community)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijbesd.v7i3.1168

Abstract

The limitations of traditional portfolio models in capturing multi-factor risks in the Indonesian capital market underlie the need for a framework that integrates a realistic return estimation model with a reliable optimization technique. Traditional portfolios do not utilize multi-factor risk and assume that market conditions depend only on a single factor; therefore, a method combining other factors, such as macroeconomic factors, is required. The research method used is the Arbitrage Pricing Theory (APT) to estimate expected stock returns based on three macroeconomic factors (CPI, Rupiah exchange rate against USD, and M2 Money Supply) and the Genetic Algorithm (GA) to determine optimal stock weights, where the resulting portfolio is then evaluated using the Sharpe Ratio to find the best portfolio composition with the highest Sharpe Ratio. The data used in this study are LQ45 stocks of the basic-materials sector in 2025. The research results show that there are four stocks selected in the formation of the optimal portfolio: ANTM, BRPT, INCO, and MDKA. Based on optimization using the Genetic Algorithm, the obtained fund allocation weight composition is 34.82% for ANTM, 16.92% for BRPT, 23.57% for INCO, and 24.69% for MDKA. The formed optimal portfolio yields a Sharpe Ratio of 0.6582, which indicates that although the portfolio generates a positive return.