Claim Missing Document
Check
Articles

Found 6 Documents
Search

Indofood CBP Sukses Makmur Tbk Stock Price Prediction Using Long Short-Term Memory (LSTM) Saputra, Moch Panji Agung; Saputra, Renda Sandi; Dwiputra, Muhammad Bintang Eighista
International Journal of Global Operations Research Vol. 6 No. 1 (2025): International Journal of Global Operations Research (IJGOR)
Publisher : iora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47194/ijgor.v6i1.363

Abstract

Fluctuating stock price movements are a challenge in the investment world, so an accurate prediction model is needed to assist decision making. This study aims to evaluate the ability of the LSTM model to predict ICBP stock prices based on historical data and will compare the results of the LSTM model predictions with actual stock price movements to determine the extent to which this model is able to capture trends and patterns of ICBP stock prices. The results show a comparison of the original price and the predicted price indicating that the model can follow market trends, although there are still deviations at some points, especially when volatility is high. Residual analysis shows a distribution of prediction errors that is close to normal, indicating that the model does not experience significant bias. In addition, evaluation of the loss function on the training and validation data confirms that the model has converged well. In the performance evaluation, the model is able to capture stock movement patterns quite well, indicated by the Mean Absolute Error (MAE) value of 0.0231, Root Mean Squared Error (RMSE) of 0.0305, and Mean Absolute Percentage Error (MAPE) of 19.21%.
SIGNAL App Review Sentiment Analysis using Support Vector Machine (SVM) on Google Play Store Comments Saputra, Moch Panji Agung; Dwiputra, Muhammad Bintang Eighista
Operations Research: International Conference Series Vol. 6 No. 1 (2025): Operations Research International Conference Series (ORICS), March 2025
Publisher : Indonesian Operations Research Association (IORA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47194/orics.v6i1.366

Abstract

The SIGNAL (National Digital Samsat) application is a digital innovation that makes it easier to pay motor vehicle taxes in Indonesia. This study aims to analyze user sentiment towards the SIGNAL application through reviews on the Google Play Store, using Support Vector Machine (SVM) as a classification method. The analysis process includes the stages of review data collection, pre-processing (text cleaning, tokenization, stopword removal, and stemming), text transformation to numeric features using Term Frequency-Inverse Document Frequency (TF-IDF), and SVM model training. The dataset is taken from 10,000 of the latest reviews consisting of reviews classified into three sentiment categories: positive, negative, and neutral. The evaluation results show that the SVM model has a high accuracy of 91%, with consistent precision, recall, and F1-score values ​​in each sentiment category. Positive sentiment dominates reviews (59%), followed by negative sentiment (33.8%) and neutral (7.2%). This analysis provides valuable insights for developers to improve the quality of applications, especially in understanding user needs and expectations.
Implementing EfficientNetB0 for Facial Recognition in Children with Down Syndrome Pirdaus, Dede Irman; Dwiputra, Muhammad Bintang Eighista; Saputra, Moch Panji Agung
Operations Research: International Conference Series Vol. 6 No. 2 (2025): Operations Research International Conference Series (ORICS), June 2025
Publisher : Indonesian Operations Research Association (IORA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47194/orics.v6i2.383

Abstract

Early detection of Down Syndrome in children is crucial to provide more appropriate medical and educational interventions. This study aims to build and evaluate a deep learning-based classification model using the EfficientNetB0 architecture to distinguish facial images of children with Down Syndrome and healthy children. The dataset used consists of two classes (Down Syndrome and healthy), which have gone through an augmentation process to increase data diversity and prevent overfitting. The model was trained using the Adam algorithm with a learning rate of 0.0001 and a sparse categorical crossentropy loss function for 10 epochs. The training results showed that the model achieved a validation accuracy of 93.94%, with the lowest validation loss value of 0.2390. Further evaluation was carried out using a confusion matrix, which showed that the model was able to properly classify 312 out of 333 Down Syndrome images and 309 out of 330 healthy children images, resulting in an overall accuracy of 94%. In addition, the precision, recall, and f1-score values ​​for both classes were in the range of 0.94, indicating a balanced and strong performance. Visual analysis of the misclassified images indicates that some misclassifications occur on healthy children’s faces with certain expressions, angles, or lighting conditions that resemble Down syndrome. Conversely, some children with Down syndrome are also predicted as healthy when their facial features are not too prominent or similar to normal children under certain lighting conditions. This shows that despite the high performance of the model, sensitivity to facial feature variations remains a challenge.
Comparison of Grid Search and Random Search Effectiveness in Parameter Tuning on Electric Car Sentiment Analysis Saputra, Moch Panji Agung; Dwiputra, Muhammad Bintang Eighista
International Journal of Global Operations Research Vol. 6 No. 2 (2025): International Journal of Global Operations Research (IJGOR), May 2025
Publisher : iora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47194/ijgor.v6i2.371

Abstract

The increasing use of electric cars in Indonesia has prompted many public discussions recorded on various digital platforms. This study aims to classify public sentiment towards the implementation of electric cars through comment analysis using the XGBoost Classifier model. The data used were obtained from the Kaggle platform, in the form of public comments that have gone through pre-processing stages, such as removing empty data, label encoding, and visualizing class distribution. Furthermore, the data was divided into training, validation, and test data using stratification techniques, and data imbalance was handled using the SMOTE method. Modeling was carried out using the XGBoost Classifier algorithm, then hyperparameter tuning was carried out using two approaches, namely Random Search and Grid Search. The parameters tested included learning_rate, max_depth, n_estimators, subsample, colsample_bytree, gamma, alpha, and lambda. The experimental results showed that the model without tuning produced an accuracy of 67%. After tuning, Random Search increased its accuracy to 68%, while Grid Search achieved the highest accuracy of 69%. Based on evaluation using precision, recall, f1-score, and accuracy metrics, tuning with Grid Search is proven to provide more optimal results compared to other methods. This study shows that systematic hyperparameter tuning can improve the performance of sentiment classification models.
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

Abstract

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.
Implementation of Machine Learning Model for Pest Classification in Rice Plants Saputra, Moch Panji Agung; Setyawan, Deva Putra; Dwiputra, Muhammad Bintang Eighista
International Journal of Research in Community Services Vol. 6 No. 3 (2025): International Journal of Research in Community Service (IJRCS)
Publisher : Research Collaboration Community (Rescollacom)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijrcs.v6i3.957

Abstract

Rice cultivation is a cornerstone of food security in agrarian countries like Indonesia, yet it remains highly vulnerable to pest infestations that can severely impact crop productivity. Manual identification of pests is time-consuming and error-prone, especially when pest species exhibit similar morphological characteristics. This study aims to implement and evaluate the performance of four classical machine learning algorithms Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), and Logistic Regression (LR) for classifying rice pests based on image data. The dataset, derived from Kaggle’s “Rice Pest Detection Dataset,” includes 12 pest classes and underwent a series of preprocessing steps: grayscale conversion, image resizing to 128×128 pixels, feature extraction using Histogram of Oriented Gradients (HOG), label encoding, and class balancing via SMOTE. The experimental setup used 80% of the data for training and 20% for testing. Performance was evaluated using precision, recall, F1-score, and confusion matrices. Among the four models, SVM achieved the most consistent and robust performance, with F1-scores reaching up to 0.98 in several pest classes and an overall balanced classification across the dataset. Random Forest followed closely, particularly excelling in distinguishing classes such as Rice Water Weevil and Yellow Rice Borer, achieving F1-scores of 0.99 and 0.96 respectively. In contrast, KNN showed signs of overfitting, with extreme precision-recall imbalances, while LR was more stable but less accurate in separating visually similar classes like Rice Stem Fly and Thrips. Visual analysis of correct and incorrect predictions revealed that classes 7 (Rice Stem Fly) and 11 (Thrips) were consistently misclassified across all models, likely due to high visual similarity.