cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Devni Prima Sari
Contact Email
devniprimasari@fmipa.unp.ac.id
Phone
+6285868648474
Journal Mail Official
mjomaf@ppj.unp.ac.id
Editorial Address
Data Analytics, Mathematical Modelling, and Forecasting (DMF) Research Group Department of Mathematics Faculty of Mathematics and Natural Sciences Universitas Negeri Padang Jalan Prof. Dr. Hamka, Air Tawar Padang, Sumatera Barat Web: mjomaf.ppj.unp.ac.id Email: mjomaf@ppj.unp.ac.id
Location
Kota padang,
Sumatera barat
INDONESIA
Mathematical Journal of Modelling and Forecasting
Published by Universitas Negeri Padang
ISSN : -     EISSN : 29881013     DOI : https://doi.org/10.24036/mjmf.v1i2
Core Subject : Economy, Science,
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance
The Mathematical Journal of Modelling and Forecasting are scientific journals in the fields of mathematics, statistics, actuarial, financial mathematics, computational mathematics, and applied mathematics. This journal is published twice a year, precisely in June and December in an online version. All publications are available in full text and free to download.
Arjuna Subject : Matematika - Matematika Terapan
Articles 33 Documents
 1   2   3   4 
Enhancing Oil Field Investment Decisions Using Spiral Dynamics Optimization Humairah, Reni; Afrizal, Aidil Adrianda; Kartika, Hanum
Mathematical Journal of Modelling and Forecasting Vol. 3 No. 1 (2025): June 2025
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/mjmf.v3i1.38

Abstract

Investment is an activity in the present to obtain profits in the future. One method of investment assessment is calculating Net Present Value (NPV) using Discounted Cash Flow (DCF). To determine the right time to carry out an investment in order to obtain maximum profits, it is necessary to determine a time limit for when the investment should be carried out or not. Then, the threshold curve (optimal implementation time limit) for the investment will first be determined. After obtaining the threshold curve for each investment option, the NPV value for each investment option will then be determined. The best investment choice is the one that provides the highest NPV value. The metaheuristic method is an effective optimization method for determining the optimal investment implementation time limit (threshold curve). One metaheuristic method for determining threshold curves is the Spiral Dynamics Optimization algorithm developed by Kenichi Tamura and Keiichiro Yasuda, a search algorithm inspired by phenomena in nature such as water speed, air pressure speed, Nautilus Shells, and spiral galaxy shapes. The results of this research are areas that are above the threshold curve, which can implement the project, while areas that are below the curve are not recommended for implementing the project.
Risk Comparison in Optimal Portfolios: A Study of Value at Risk (VaR) and Tail Value at Risk (TVaR) Turnika Afdatul Rafni; Dina Agustina
Mathematical Journal of Modelling and Forecasting Vol. 3 No. 1 (2025): June 2025
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/mjmf.v3i1.40

Abstract

Considering investment risk is something that investors must do before deciding to invest; measuring risk provides an opportunity for investors to get the desired return and minimize losses. This study compares Value at Risk (VaR) and Tail Value at Risk (TVaR) methodologies for measuring portfolio risk. VaR is a commonly used method that provides the maximum loss at a certain confidence level and period. However, VaR is not an effective measure of risk because it does not satisfy one of the axioms of coherent risk measures, i.e., subadditivity. Subsequently, the TVaR measure emerged, which satisfies all the axioms of coherent risk measures, thereby providing a good and effective measure of risk. The optimal portfolio will be formed using the Single Index model, simplifying the Markowitz portfolio model. The Composite Stock Price Index will be the only factor influencing other stocks in this model. The data used data from stocks that were consistently listed on the IDX30 index from 24/10/2022 to 25/10/2024. Based on the result of the analysis of data, the optimal portfolio consists of 5 stocks, i.e., PT Bank Mandiri (BMRI.JK), PT Indofood Sukses Makmur (INDF.JK), PT Bank Central Asia (BBCA.JK), PT Bank Negara Indonesia (BBNI.JK), and PT Barito Pacific (BRPT.JK). Risk measures were compared on the optimal portfolio, using a confidence level of 1-α=95%, with a daily time period, and an initial investment capital of IDR 1 billion. The estimated VaR risk measure is IDR 15.38 million, while TVaR reaches IDR 23.25 million.
Strategy for Enhancing GRU-RNN Performance through Parameter Optimization Hermansah
Mathematical Journal of Modelling and Forecasting Vol. 3 No. 1 (2025): June 2025
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/mjmf.v3i1.41

Abstract

This study examines the selection of optimal parameters in the Gated Recurrent Unit-Recurrent Neural Network (GRU-RNN) model for forecasting inflation in Indonesia. Accurate forecasting requires precise model parameter adjustments, especially for time-series data, which can be either linear or non-linear. The study evaluates several parameters, including learning rate, number of epochs, optimization methods (Stochastic Gradient Descent (SGD) and Adaptive Gradient (AdaGrad)), and activation functions (Logistic, Gompertz, and Tanh). The results show that the best combination consists of the SGD optimization method, logistic activation function, a learning rate of 0.05, and 450 epochs, which delivers the best performance by minimizing errors and achieving high prediction accuracy. When compared to other forecasting models such as Exponential Smoothing (ETS), Autoregressive Integrated Moving Average (ARIMA), Feedforward Neural Network (FFNN), and Recurrent Neural Network (RNN), the GRU-RNN model shows significant superiority. Additionally, the Logistic activation function proves to be more effective in maintaining stability and prediction accuracy, while the use of the Adaptive Gradient (AdaGrad) method results in lower performance. These findings underscore the GRU-RNN model's ability to handle non-linear time-series data and provide insights for developing more accurate and efficient forecasting models in the future.

Page 4 of 4 | Total Record : 33

 1   2   3   4 

Filter by Year

2023 2025


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2025): June 2025 Vol. 2 No. 2 (2024): December 2024 Vol. 2 No. 1 (2024): June 2024 Vol. 1 No. 2 (2023): December 2023 Vol. 1 No. 1 (2023): June 2023