Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : International Journal of Quantitative Research and Modeling

Mathematical Modeling of Pulling Force in Tug of War Competitions: A Tribute to Indonesia's Independence Anniversary Pirdaus, Dede Irman; Laksito, Grida Saktian; Hidayana, Rizki Apriva
International Journal of Quantitative Research and Modeling Vol 5, No 3 (2024)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v5i3.754

Abstract

Tug of war is a folk game that uses a mining tool (rope). How to play a team with 2 teams facing each other. Each team consists of 3 or more people, who face each other holding the mine to be pulled. This tug-of-war competition activity is to train body strength, teamwork and cohesiveness. Once the second mark on the rope from the center red mark crosses the center line, the team that pulls the rope to their area wins the game. In this tug of war game there are many styles, including: Frictional Force, Tensile Force, Gravitational Force, and Muscular Force. This paper aims to study the physical forces of tug of war with a mathematical model based on the physical phenomena that exist in the game of tug of war. This model is created by considering tug of war as two objects connected by a rope. The analysis is done by considering the forces acting in the model. The results show that if after being pulled with a force F, the object moves to the right with an acceleration of a, then the acceleration of the object is based on the equation of motion according to Newton's law.
Implementation of the Gated Recurrent Unit (GRU) Model for Bank Mandiri Stock Price Prediction Saputra, Renda Sandi; Pirdaus, Dede Irman; Saputra, Moch Panji Agung
International Journal of Quantitative Research and Modeling Vol 6, No 1 (2025)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v6i1.894

Abstract

Stock price prediction is a crucial aspect in the financial world, especially in making investment decisions. This study aims to analyze the performance of the Gated Recurrent Unit (GRU) model in predicting Bank Mandiri (BMRI.JK) stock prices using historical data for five years. Stock data was collected from Yahoo Finance and normalized using Min-Max Scaling to improve model stability. Furthermore, the windowing technique was applied to form a dataset that fits the architecture of the time series forecasting-based model. The developed GRU model consists of two GRU layers with 128 neuron units, two dropout layers to prevent overfitting, and one output layer with one neuron to predict stock prices. Model evaluation was carried out using the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared (R² Score) metrics. The experimental results show that the GRU model is able to produce predictions with a high level of accuracy, indicated by the R² Score value of 0.9636, which indicates that the model can explain 96.36% of stock price variability based on historical data.
Implementation of the Gated Recurrent Unit (GRU) Model for Bank Mandiri Stock Price Prediction Saputra, Moch Panji Agung; Saputra, Renda Sandi; Pirdaus, Dede Irman
International Journal of Quantitative Research and Modeling Vol. 6 No. 1 (2025)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v6i1.894

Abstract

Stock price prediction is a crucial aspect in the financial world, especially in making investment decisions. This study aims to analyze the performance of the Gated Recurrent Unit (GRU) model in predicting Bank Mandiri (BMRI.JK) stock prices using historical data for five years. Stock data was collected from Yahoo Finance and normalized using Min-Max Scaling to improve model stability. Furthermore, the windowing technique was applied to form a dataset that fits the architecture of the time series forecasting-based model. The developed GRU model consists of two GRU layers with 128 neuron units, two dropout layers to prevent overfitting, and one output layer with one neuron to predict stock prices. Model evaluation was carried out using the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R-squared (R² Score) metrics. The experimental results show that the GRU model is able to produce predictions with a high level of accuracy, indicated by the R² Score value of 0.9636, which indicates that the model can explain 96.36% of stock price variability based on historical data.