cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota makassar,
Sulawesi selatan
INDONESIA
JURNAL MATEMATIKA STATISTIKA DAN KOMPUTASI
Published by Universitas Hasanuddin
ISSN : 18581382     EISSN : 26148811     DOI : -
Core Subject : Education,
Mathematics
Jurnal ini mempublikasikan paper-paper original hasil-hasil penelitian dibidang Matematika, Statistika dan Komputasi Matematika.
Arjuna Subject : -
Articles 514 Documents
 48   49   50   51   52 
Determination of Joint Life Term Insurance Premium Reserves Using the Prospective Method Based on the Cox-Ingersoll-Ross (CIR) Stochastic Interest Rate Model Prihatin Sihotang; Siska Yosmar; Septri Damayanti
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.48922

Abstract

Premium reserves are the minimum funds that insurance companies are required to set aside to guarantee the fulfillment of long-term contractual obligations to policyholders in the future. Good management of premium reserves is very important to maintain the financial stability of insurance companies. This study aims to determine the premium reserves for joint life term life insurance using a prospective method based on the CIR model stochastic interest rate. This study uses a literature review method, with calculations based on the 2019 Indonesian Mortality Table (TMI) and historical BI interest rate data for estimating CIR model parameters. The calculation results show that premium reserves tend to increase at the beginning of the period and decrease towards the end of the period. Compared to fixed interest rates, premium reserves using CIR model interest rates are higher in each period.
Sustainable Stock Screening Based on Fundamental and Technical Indicators using Gaussian Naive Bayes Classifier Risky Gunawan; Cinta Priscillia Maharani; Gita Fitriyana; Dwi Indah Maharani
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.49168

Abstract

Investors increasingly require systematic methods for sustainable stock screening, particularly for ESG-focused benchmarks like Inodnesia's SRI-KEHATI Index. This Study addresses a gap by developing and evaluating a stock screening framework using a Gaussian Naive Bayes (GNB) classifier to integrate both fundamental and technical analysis. The model utilized quarterly data from 25 SRI-KEHATI stocks from Q1 2024 to Q2 2025, training on 11 indicators to predict future quarterly returns, classifying stocks as "Investable" (Label 1) or "Non-investable" (Label 0). The model achieved an average training accuracy of 73.6%. Feature importance analysis revealed that technical indicators, such as Average Log Return, Average MACD, Average RSI, and key fundamental ratios, PBV and ROA, were the most influential predictors. Model predictions were evaluated through a simple equal-weighted portfolio simulation for Q3 2025. The simulation results showed the model-selected "Investable" portfolio generated a 29.9% return, substantially outperforming and the "Non-investable" portfolio (3.56%). These findings demonstrate that the GNB classifier is an effective framework for sustainable stock screening, successfully identifying ESG-compliant stocks that also deliver superior financial returns and providing a practical tool for responsible investing in the Indonesian capital market.
Statistical Downscaling Using the Kibria–Lukman Regression with Dummy Variables for Rainfall Forecasting Sitti Sahriman; Syamsuddin Toaha; Anisa Kalondeng; M. Zaky Hisyam Gozhi; Aidul Fitri Mustamin
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.49179

Abstract

Global Circulation Models (GCM) are widely used to project climate variables at the global scale. However, the relatively coarse spatial resolution of GCM outputs makes direct GCM-based climate forecasting generally less accurate at the local scale. To bridge this scale mismatch, this study applies statistical downscaling (SD). The main challenge in GCM-based SD is the large number of predictor (grid) variables that are strongly correlated, which induces multicollinearity and can reduce the stability of coefficient estimation. To address this issue, Kibria-Lukman Regression (KLR) is used, which is a shrinkage method that combines the variance-reduction property of Ridge Regression (RR) with the bias-control concept of Liu Regression (LR). This study aims to obtain the best SD model and to produce local rainfall forecasting in Pangkep Regency during the 2023–2024 testing period. The research stages included: (1) developing an SD model using KLR with the addition of dummy variables as additional predictors; and (2) evaluating the forecasts using testing data. The results showed that the KLR model with dummy variables provided the best performance, with an RMSE of 73.002 and a coefficient of determination (R²) of 94.069%. At the validation stage, the model also produced a high pattern agreement (correlation of 0.936) and a relatively low forecasting error (RMSEP of 94.614), and it outperformed other multicollinearity-handling approaches. Thus, the proposed model has the potential to serve as a tool for local-scale rainfall forecasting to support salt production planning in Pangkep Regency
Analysis of the Effects of Light Emitting Diode (LED) Phototherapy on the Hematological and Biochemical Parameters of Rabbits Using Repeated Measures Longitudinal ANOVA Dita Amelia; Suliyanto Suliyanto; Anisah Nabilah Ghasani; Nike Meliana Rahmawati; Dwi Syarifatun Nisya’; Dinda Rahma Alya
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.49375

Abstract

This study examined the longitudinal effects of Light Emitting Diode (LED) phototherapy on hematological (hemoglobin) and biochemical (creatinine) parameters in rabbits (Oryctolagus cuniculus). Although LED phototherapy is widely applied as a non-invasive treatment, its systemic effects in repeated-measure settings remain limited. Fourteen rabbits were randomly assigned to a control group (n = 7) and a treatment group (n = 7). The treatment group received two 12-hour LED phototherapy sessions on consecutive days, while the control group underwent identical conditions without LED activation. Hemoglobin and creatinine levels were measured at three time points and analyzed using Repeated Measures ANOVA, with assumption testing for normality, homogeneity, and sphericity; Greenhouse–Geisser correction was applied when necessary. The results showed that observation time significantly affected hemoglobin (p = 0.004967) and creatinine levels (p = 0.03577), indicating temporal physiological changes that occurred regardless of treatment exposure. However, no significant differences were observed between the control and treatment groups for hemoglobin (p = 0.936) or creatinine (p = 0.357), and no significant group–time interaction was detected, suggesting that the observed changes were independent of LED phototherapy. Post-hoc pairwise comparisons based on estimated marginal means (EMMs) with Tukey adjustment revealed a significant increase in hemoglobin from time 0 to time 1 and a significant difference in creatinine between time 1 and time 2, further supporting that these variations reflect natural physiological processes rather than treatment-induced effects. These findings indicate a lack of evidence of treatment effect under the studied conditions, although the relatively small sample size warrants cautious interpretation. Future studies with larger samples are recommended.
Breast Cancer Classification Model Using Decision Tree Algorithm Nuzla Af'idatur Robbaniyyah; Ismi Asmawati; Syamsul Bahri
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.49472

Abstract

Cancer is a disease characterized by the presence of abnormal cells or tissues that grow rapidly, uncontrollably, can spread to other parts of the patient's body and it can also sometimes be malignant. According to the International Agency for Research on Cancer, in 2024 breast cancer will rank second in terms of the highest number of cases and fourth as the leading cause of death globally. The objective of this study is to apply the Classification and Regression Tree (CART) decission tree algorithm to a breast cancer classification model based on patient medical records. The model developed has a specificity of 95.77%, recall, precision, and F1-Score of 93.02%, and accuracy of 94.74%. The model was evaluated using a confusion matrix to measure its performance. Thus, the CART algorithm can be applied in classification models, and the resulting model is considered optimal as it achieves percentages within the 90%-100% range for all performance evaluation metrics.  
Value-at-Risk Analysis of PT Bukit Asam Tbk (PTBA) Stock Returns Based on an ARIMA–GARCH Model with a Student-t Distribution Najwa Khoir Aldawiyah; Indana Zulfa Wulandari; Ahmad Wahyu Firmanda; M. Fariz Fadillah Mardianto
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.49505

Abstract

Stock investment involves substantial risk due to return volatility, which is particularly evident in mining sector stocks such as PT Bukit Asam Tbk (PTBA). This study aims to estimate stock return risk under high volatility and leptokurtic behavior using an ARIMA–GARCH model with a Student-t distribution, focusing on Value-at-Risk (VaR) as a risk measure. Daily PTBA stock return from closing price data from 1 October 2024 to 3 November 2025 were obtained from Investing.com. The best model is ARIMA (0,1,1)–GARCH-t (1,1), with an AIC value of −5.612 and a testing MSE of 0.0000127. The Student-t VaR is estimated at 0.023188 (95%) and 0.046318 (99%), while the Cornish–Fisher approach yields higher VaR values of 0.032674 (95%) and 0.12472 (99%). These results indicate that heavy-tailed volatility models provide more prudent risk estimates and are useful for investment risk management under extreme market conditions.    
Traffic Lights for a Five-Arm Intersection Using Petri Net Models Tomi Tristono; Setiyo Daru Cahyono; Sukadi Sukadi; Joko Triono; Seno Aji; Sudarno Sudarno; Mochamad Sidqon
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.49752

Abstract

This study aims to examine the traffic light model for a five-arm intersection. Two types of traffic light models were studied, namely the standard type and the modified Norwegian type. Traffic lights have a fixed phase scheduling sequence. The traffic light modeling method uses Petri nets to graphically represent the behavioral structure of mathematical modeling symbols in distributed discrete systems. The results of the study show that the Occurrence Graph of the standard traffic light and the modified Norwegian traffic light meet the Coverability Tree requirements for all possible finite states. The Coverability Tree method also includes the properties of boundedness and conservation, along with all transition sequences that fire. The Petri net model satisfies the live property because it never enters a deadlock or a state where no transition can fire. The Petri net model has also satisfied the Invariants property, which represents signal behavior that does not change over time. The Petri net model is declared correct and valid because it satisfies all required properties. The model can present the structure of traffic light behavior at a five-arm intersection.
Unveiling Eco-Epidemiological Risk Assessment through Bayesian Spatio-Temporal SPDE-INLA Approach Mukhsar Mukhsar; Ida Usman; Asrul Sani; La Gubu; Muzuni Muzuni; Ruslan Majid; I Putu Sudayasa; Fahmiati Fahmiati
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.49930

Abstract

Dengue hemorrhagic fever (DHF) remains a major public health burden in tropical areas. The DHF driven by nonlinear interactions, vector dynamics, and population density. Characterizing spatio-temporal risk heterogeneity is critical to targeted intervention. We analyzed dengue risk in Kendari using a Bayesian Stochastic Partial Differential Equation (SPDE) via Integrated Nested Laplace Approximation (INLA). DHF monthly data from 2022–2024 were integrated with geospatial information to estimate relative risk and spatial risk contours. Model performance was compared with Generalized Linear Models (GLM), Intrinsic Conditional Autoregressive (ICAR), and second order Random Walk (RW2). Kendari Barat and Kendari districts emerged as primary hotspots, while Kadia, Mandonga, Baruga, Kambu, and Wua-Wua were high-risk districts. Abeli, Poasia, and Puuwatu districts exhibited moderate risk. Lalodati, Soropia, and Sampara districts showed lower risk. Risk contours revealed clusters concentrated in the urban core and along major corridors, highlighting the influence of settlement density and spatial connectivity. The SPDE–INLA model outperformed GLM, ICAR, and RW2 in capturing spatial structure and improving predictive accuracy. High resolution risk estimates supported specific district including intensified source reduction before and during peak rainfall, selective fogging, larval control, community education, microclimate monitoring, and early case screening in high-risk areas.
Optimal Portfolio Formation Using a Combination of Genetic Algorithms and Particle Swarm Optimization Based on Cluster Analysis Irfan N. Amiruddin; Edy S. Rusdy
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.50039

Abstract

The formation of an optimal portfolio is one of the strategies of investors in allocating their funds so as to minimize risk while maximizing profits. The optimal portfolio formation method has evolved over the years, ranging from simple calculation methods, to using complex optimization algorithms. This study aims to group LQ-45 stocks through a clustering algorithm, then determine the right weighting of representative shares of each cluster through the combination of GA-PSO so that an optimal portfolio is produced. The research begins with data pre-processing which includes transformation and reduction of data dimensions. The data from the dimension reduction is used to group stocks into clusters based on the best clustering algorithm. The stocks with the highest Sharpe ratio in each cluster are used to form the portfolio. The performance of the weighted portfolio using GA-PSO will be compared with the weighted portfolio using PSO. The results of the study showed that the K-Means algorithm became the clustering method with the highest silhouette score, which was 0.3614, and the optimal number of clusters produced was 6. Based on the results of the K-Means algorithm, the cluster representative stocks used for portfolio formation are ANTM, BRPT, EXCL, MDKA, MEDC, and PTBA. Furthermore, the results showed that the Sharpe ratio of stock portfolios using GA-PSO combined was greater than that of portfolios that used PSO alone for weighting. The K-Means algorithm is more suitable for grouping stocks than the DBSCAN and Agglomerative algorithms with Average Linkage. Furthermore, the combination of genetic algorithms and particle swarm optimization complements each other in weighting stocks so that it produces a portfolio with more optimal performance when compared to only using particle swarm optimization.
Rupiah Exchange Rate Forecast Against the United States Dollar Using the Singular Spectrum Analysis Method Mutiara Qalbu; Etik Zukhronah; Irwan Susanto
Jurnal Matematika, Statistika dan Komputasi Vol. 22 No. 3 (2026): May 2026
Publisher : Department of Mathematics, Hasanuddin University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20956/j.v22i3.50120

Abstract

Singular Spectrum Analysis (SSA) is a nonparametric time series forecasting method that decomposes a time series into signal and noise components without relying on predetermined model assumptions. This study aims to forecast the rupiah exchange rate against the United States Dollar (USD) using the Singular Spectrum Analysis (SSA) method based on data from the period August 2023 to August 2024. The in-sample data consists of 191 points from August 1, 2023, to May 21, 2024, while the out-of-sample data consists of 48 points from May 22, 2024, to August 1, 2024. The results showed that the SSA method achieved Mean Absolute Percentage Error (MAPE) values of 0.44% on in-sample data and 0.64% on out-of-sample data, indicating that the method is quite effective in predicting the rupiah exchange rate against the USD.

Page 51 of 52 | Total Record : 514

 48   49   50   51   52 

Filter by Year

2005 2026


Reset
Filter By Issues
All Issue Vol. 22 No. 3 (2026): May 2026 Vol. 21 No. 2 (2025): JANUARY 2025 Vol. 21 No. 1 (2024): SEPTEMBER 2024 Vol. 20 No. 3 (2024): May 2024 Vol. 20 No. 2 (2024): JANUARY 2024 Vol. 20 No. 1 (2023): SEPTEMBER, 2023 Vol. 19 No. 3 (2023): MAY, 2023 Vol. 19 No. 2 (2023): JANUARY 2023 Vol. 19 No. 1 (2022): SEPTEMBER, 2022 Vol. 18 No. 3 (2022): MAY, 2022 Vol. 18 No. 2 (2022): JANUARY 2022 Vol. 18 No. 1 (2021): September 2021 Vol. 17 No. 3 (2021): May, 2021 Vol. 17 No. 2 (2021): JANUARY 2021 Vol. 17 No. 1 (2020): JMSK, SEPTEMBER, 2020 Vol. 16 No. 3 (2020): JMSK, MAY, 2020 Vol. 16 No. 2 (2020): JMSK, JANUARY, 2020 Vol. 15 No. 2 (2019): JMSK Vol. 15, No. 2, January 2019 Vol. 16 No. 1 (2019): JMSK, July, 2019 Vol. 15 No. 1 (2018): July 2018 Vol. 14 No. 2 (2018): January 2018 Vol. 14 No. 1 (2017): July 2017 Vol. 13 No. 2 (2017): January 2017 Vol. 13 No. 1: July 2016 Vol. 12 No. 2: January 2016 Vol. 12 No. 1: July 2015 Vol. 11 No. 2: January 2015 Vol. 11 No. 1: July 2014 Vol. 10 No. 2: January 2014 Vol. 10 No. 1: July 2013 Vol. 9 No. 2: January 2013 Vol. 9 No. 1: July 2012 Vol. 8 No. 2: January 2012 Vol. 8 No. 1: July 2011 Vol. 7 No. 2: January 2011 Vol. 7 No. 1: July 2010 Vol. 6 No. 2: January 2010 Vol. 6 No. 1 (2009): July 2009 Vol. 5 No. 2: January 2009 Vol. 5 No. 1: July 2008 Vol. 4 No. 2: January 2008 Vol. 4 No. 1: July 2007 Vol. 3 No. 2: January 2007 Vol. 3 No. 1: July 2006 Vol. 2 No. 2: January 2006 Vol. 2 No. 1: July 2005 More Issue