Garuda - Garba Rujukan Digital

Stock Portfolio Optimization of Several Companies Engaged in Renewable Energy for Investment Decision-Making Using the Markowitz Model Saputra, Moch Panji Agung; Saputra, Renda Sandi
International Journal of Business, Economics, and Social Development Vol 5, No 4 (2024)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijbesd.v5i4.805

This study focuses on optimizing the renewable energy company's stock portfolio using the Markowitz model, which aims to balance risk and return for proper investment decision making. With the increasing demand for clean energy, portfolio optimization in the renewable energy sector is important for investors. This research takes into account historical stock performance and applies the Mean-Variance Optimization framework to minimize risk while maximizing return. This portfolio consists of selected renewable energy companies, and the analysis runs from September 2021 to August 2024. This study aims to analyze the allocation of investment portfolios in renewable energy company stocks in Indonesia. Based on the analysis results, the investment portfolio is allocated to five main stocks, namely BUMI.JK with an investment value of IDR 17,075,844 (17.08%), INDY.JK of IDR 5,825,852 (5.83%), KEEN.JK of IDR 33,766,798 (33.77%), RAJA.JK of IDR 43,084,876 (43.08%), and WIKA.JK of IDR 246,630 (0.25%). These results indicate that most of the funds are invested in RAJA.JK and KEEN.JK stocks, which contribute more than 75% of the total investment portfolio.

Markowitz Portfolio Learning Design in Financial Mathematics with Technology-Based Stock Investment Simulation Practice Saputra, Moch Panji Agung; Saputra, Renda Sandi; Laksito, Grida Saktian
International Journal of Research in Community Services Vol 6, No 1 (2025)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijrcs.v6i1.846

In an era of global economic uncertainty, mastering the concept of portfolio management is important for students in preparing themselves to face the challenges of the financial world. This study aims to design financial mathematics learning by integrating Markowitz's portfolio theory and technology-based stock investment simulation practices. The approach used includes the use of digital platforms to obtain historical stock data and stock market simulations for virtual investment practices. The results of the study indicate that the use of this method can improve students' understanding of the concepts of diversification, expected returns, and risk management in investment portfolios. With an interactive and practical approach, students can gain direct experience in building an optimal portfolio based on the Markowitz mean-variance model and implementing it in stock investment simulations. This study makes a significant contribution to the development of students' financial literacy by utilizing digital technology effectively.

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

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.

Comparative Analysis of LSTM and GRU Models for Ethereum (ETH) Price Prediction Saputra, Moch Panji Agung; Ibrahim, Riza Andrian; Saputra, Renda Sandi
International Journal of Business, Economics, and Social Development Vol 6, No 1 (2025)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijbesd.v6i1.887

The increasing use of cryptocurrencies has changed the dynamics of investment, presenting both opportunities and challenges for investors. Although various studies have compared the performance of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) in predicting financial asset prices, there are still differences in results regarding which model is superior. Therefore, this study aims to compare the performance of LSTM and GRU in predicting Ethereum prices using a hyperparameter tuning approach. The data used is historical data of Ethereum (ETH) shares from 2020 to 2025. The research methodology includes data preprocessing using Min-Max scaling, model development with various layer configurations, and comprehensive evaluation using several performance metrics. The results show that the GRU Model provides superior performance with a lower Root Mean Squared Error (RMSE) of 0.0234 and Mean Absolute Error (MAE) of 0.0168, compared to LSTM's RMSE of 0.0265 and MAE of 0.0193. While LSTM exhibits a slightly better Mean Absolute Percentage Error (MAPE) of 18.08% compared to GRU at 18.17%, the GRU model achieves a higher R² Score of 0.9442 compared to LSTM at 0.9282. Visual analysis of the prediction patterns and residual distributions further demonstrates GRU’s more consistent and accurate performance in capturing Ethereum price movements. These findings suggest that while both models are effective for cryptocurrency price prediction, GRU offers slightly better overall performance and stability, especially in maintaining consistent prediction accuracy across different market conditions.

Community Readiness for the Use of the Cash on Delivery (COD) Application Without a Marketplace Using an SPSS-based Likert Scale: Community Readiness for the Use of the Cash on Delivery (COD) Application Without a Marketplace Using an SPSS-based Likert Scale Saputra, Renda Sandi; Salih, Yasir
International Journal of Mathematics, Statistics, and Computing Vol. 1 No. 3 (2023): International Journal of Mathematics, Statistics, and Computing
Publisher : Communication In Research And Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijmsc.v1i3.5

This study aims to analyze the community's readiness for the Cash on Delivery (COD) without marketplace application as a payment method in online shopping transactions. Questionnaires were distributed to 30 respondents aged 18 to 25 years with various levels of education. The results of the questionnaire were analyzed using the SPSS statistical software, and the data obtained included age, gender, education level, and responses to several questions that were relevant to community readiness for COD services. The results of the analysis show that the majority of the community shows a high level of readiness for the COD application, with around 50.0% to 60.0% of respondents belonging to the ready and very ready categories. The diverse age range of respondents indicates that the COD application can reach young age groups, and the varying levels of education indicate that this application attracts interest from various walks of life. The gender of the respondents did not show a significant difference in the level of interest in COD services. Even though the majority showed high readiness, there were some respondents who showed a lower level of readiness. Therefore, a special approach is needed to provide further information and education to this group to increase their readiness to use COD services. In conclusion, the COD application has great potential to become a popular and reliable choice for users to make purchases online. However, effective marketing, education and product development efforts need to be continued to reach the full potential of COD services and provide better benefits to potential users. By focusing on good user experience, data security, and the right marketing strategy, COD applications have a chance of success in a competitive market.

Optimization of Renewable Energy Company Stock Portfolio for Investment Decision Making using the Markowitz Model Saputra, Renda Sandi; Rahayu, Alpi fauziah; Suhaimi, Nurnisaa Binti Abdullah
International Journal of Mathematics, Statistics, and Computing Vol. 2 No. 4 (2024): International Journal of Mathematics, Statistics, and Computing
Publisher : Communication In Research And Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijmsc.v2i4.142

This study focuses on optimizing the renewable energy company's stock portfolio using the Markowitz model, which aims to balance risk and return for proper investment decision making. With the increasing demand for clean energy, portfolio optimization in the renewable energy sector is important for investors. This research takes into account historical stock performance and applies the Mean-Variance Optimization framework to minimize risk while maximizing return. This portfolio consists of selected renewable energy companies, and the analysis runs from September 2021 to August 2024. This study aims to analyze the allocation of investment portfolios in renewable energy company stocks in Indonesia. Based on the analysis results, the investment portfolio is allocated to five main stocks, namely BUMI.JK with an investment value of IDR 17,075,844 (17.08%), INDY.JK of IDR 5,825,852 (5.83%), KEEN.JK of IDR 33,766,798 (33.77%), RAJA.JK of IDR 43,084,876 (43.08%), and WIKA.JK of IDR 246,630 (0.25%). These results indicate that most of the funds are invested in RAJA.JK and KEEN.JK stocks, which contribute more than 75% of the total investment portfolio

Stock Price Prediction of PT. Pertamina Geothermal Energy Tbk Using Gated Recurrent Unit (GRU) Model Saputra, Renda Sandi; Hasan, Mohammad Tanzil; Azahra, Astrid Sulistya
International Journal of Mathematics, Statistics, and Computing Vol. 3 No. 2 (2025): International Journal of Mathematics, Statistics, and Computing
Publisher : Communication In Research And Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijmsc.v3i2.203

This study aims to predict the stock price of PT. Pertamina Geothermal Energy Tbk (PGEO.JK) using the Gated Recurrent Unit (GRU) model, a neural network architecture in the Recurrent Neural Network (RNN) category that is known to be effective in handling time series data. The data used is historical stock price data from 2022 to 2024 taken from Yahoo Finance. The GRU method was chosen because of its ability to remember long-term information and overcome the vanishing gradient problem. In the research process, the data was divided into two parts, namely training data and testing data. The GRU model was trained without adjusting hyperparameters to measure its performance by default. Model evaluation was carried out using the Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R²) metrics. The results of the study indicate that the GRU model is able to provide good prediction results with an RMSE value of 0.0271, MAE of 0.0180, MAPE of 22.25%, and an R² value of 0.9112. These values indicate that the GRU model is quite accurate in predicting the price of PGEO.JK shares. These findings indicate that GRU is a potential method in stock prediction analysis, especially in the renewable energy sector.

Development and Impact of the Use of Slang on Instagram Social Media on Teenagers and Society: Case Study of Indonesian in the Digital Era: Development and Impact of the Use of Slang on Instagram Social Media on Teenagers and Society: Case Study of Indonesian in the Digital Era Saputra, Renda Sandi; Salih, Yasir
International Journal of Linguistics, Communication, and Broadcasting Vol. 1 No. 4 (2023): International Journal of Linguistics, Communication, and Broadcasting
Publisher : Communication In Research And Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijlcb.v1i4.21

The use of slang in Instagram social media among teenagers has become a significant phenomenon. This article investigates the factors that influence the use of slang and its impact on adolescents. The results of the study show that the development of the times, the influence of the internet and electronic media have contributed to the spread of slang. The impact of using slang includes expression of positive identity and more intimate communication, but also includes the potential for decreased interest in good and correct Indonesian, ambiguity in official vocabulary, and negative use. In this digital era, it is important to understand the consequences of using slang on social media and how education and awareness about proper language can help young people overcome this challenge.

Comparison of Random Forest and SVM Algorithms in Classification of Diabetic Retinopathy Based on Fundus Image Texture Features Saputra, Renda Sandi; Saputra, Moch Panji Agung
International Journal of Quantitative Research and Modeling Vol 6, No 2 (2025)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v6i2.1011

Diabetic Retinopathy (DR) is a microangiopathic complication of diabetes mellitus that can cause visual impairment to permanent blindness. Early detection of DR is essential to prevent disease progression, but conventional methods require time, cost, and expertise that are not always available. This study aims to compare the performance of the Random Forest (RF) and Support Vector Machine (SVM) algorithms in DR classification based on texture features extracted from retinal fundus images. The dataset used consists of 3,000 retinal fundus images obtained from the Kaggle platform, divided into 2,400 training data and 600 test data. Image preprocessing includes conversion to grayscale, resizing to a resolution of 128×128 pixels, and normalization. Feature extraction is performed using a combination of Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) to produce a 14-dimensional feature vector. Performance evaluation uses accuracy, precision, recall, F1-score, ROC curve, and 5-fold cross-validation metrics. The results showed that Random Forest significantly outperformed SVM with an accuracy of 96% compared to 64%, an AUC value of 0.99 compared to 0.72, and an average cross-validation accuracy of 94.5% compared to 63.42%. Random Forest also showed balanced performance in both classes with precision, recall, and F1-score of 0.96, while SVM experienced classification imbalance especially in the disease class. This study proves that Random Forest is a more optimal algorithm for an automatic DR detection system based on fundus image texture features and can support increasing the accessibility of DR screening in areas with limited specialist medical personnel.

Optimization of Machine Learning Models for Sentiment Analysis of TikTok Comment Data on the Progress of the Ibu Kota Nusantara as New Capital City of Indonesia Saputra, Renda Sandi; Dwiputra, Muhammad Bintang Eighista; Saputra, Moch Panji Agung; Ismail, Muhammad Iqbal Al-Banna
International Journal of Mathematics, Statistics, and Computing Vol. 3 No. 3 (2025): International Journal of Mathematics, Statistics, and Computing
Publisher : Communication In Research And Publications

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijmsc.v3i3.232

Sentiment analysis plays a crucial role in understanding public opinion on social media platforms, especially in discussions related to government policies such as the relocation of Indonesia’s new capital city, known as Ibu Kota Nusantara (IKN). While machine learning algorithms like Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression (LR) are widely used for sentiment classification tasks, previous studies often focus on performance comparisons without addressing the impact of data imbalance or regularly optimizing model parameters. These issues can lead to suboptimal classification performance, especially in real-world social media data. This study aims to improve the accuracy and robustness of sentiment classification by applying two enhancement strategies: text data augmentation and hyperparameter tuning. Three models Naïve Bayes, SVM, and Logistic Regression were trained and evaluated in three experimental stages: (1) using original data, (2) after applying augmentation, and (3) after augmentation combined with hyperparameter tuning via GridSearchCV. The evaluation results show progressive improvements across the three stages. In the first stage (original data), Logistic Regression achieved the highest accuracy of 80.41%, while Naïve Bayes and SVM reached 79.73% and 76.98%, respectively. However, all models struggled to classify the minority class (positive sentiment), as reflected in their lower recall and F1-scores. After applying augmentation, performance improved significantly across all models. SVM, in particular, reached an accuracy of 92.77%, followed by Logistic Regression (86.57%) and Naïve Bayes (86.22%), with better balance between precision and recall for both sentiment classes. hyperparameter tuning further optimized model performance. Logistic Regression became the best-performing model, achieving an accuracy of 93.80%, along with high precision, recall, and F1-scores for both classes. SVM and Naïve Bayes also showed stable improvements, with accuracies of 92.88% and 87.72%, respectively.

Title

Found 19 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 19 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 19 Documents
Search