Article Per Year (5 Year)
p-Index From 2021 - 2026
1.066
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) JUITA : Jurnal Informatika Inferensi Euler : Jurnal Ilmiah Matematika, Sains dan Teknologi Journal of Mathematics, Computation and Statistics (JMATHCOS) Teknobuga : Jurnal Teknologi Busana dan Boga
Gerry Alfa Dito
IPB University
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Engineering Mathematics Social Sciences

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Making Sense of Fashion Feedback : Comparing Two Popular Text Analysis Tools Muhammad Syafiq; Wawan Saputra; Carlya Agmis Aimandiga; Cici Suhaeni; Bagus Sartono; Gerry Alfa Dito
TEKNOBUGA: Jurnal Teknologi Busana dan Boga Vol. 13 No. 1 (2025)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/teknobuga.v13i1.25930

Abstract

The rapid expansion of the fashion industry, propelled by digital technology and e-commerce, has resulted in a significant volume of customer-generated reviews. These reviews serve as a valuable source for understanding customer satisfaction and behavior. This study aims to (1) analyze customer sentiment, (2) predict product recommendations, and (3) examine the relationship between sentiment classification and recommendation decisions using text embeddings from Word2Vec and GloVe. The research utilized over 23,000 fashion product reviews sourced from Kaggle. Text data were preprocessed and vectorized using Word2Vec and GloVe, followed by classification and prediction tasks using six machine learning models: Random Forest, SVM, Naïve Bayes, LSTM, Logistic Regression, and Gradient Boosting. The results revealed that Word2Vec consistently outperformed GloVe across all models and tasks, with the Word2Vec-LSTM combination achieving the highest accuracy of 87.35% and F1 score of 92.35% in imbalanced data scenarios. Correlation analysis also confirmed a strong and statistically significant relationship between sentiment and recommendation labels, with Spearman’s Rho of 0.8340 and Kendall’s Tau of 0.8120. These findings suggest that high-quality sentiment representation can effectively support product recommendation systems. This study contributes to the understanding of embedding effectiveness in fashion-related text analysis and opens avenues for hybrid and transformer-based representations in future research.
Evaluation of Tree-Based Models for Predicting Social Assistance Recipient Status Based on National Socio-Economic Survey (SUSENAS) 2024 Yani Prihantini Hiola; Zulhijrah; I Gusti Ngurah Sentana Putra; Syella Zignora Limba; Bagus Sartono; Aulia Rizki Firdawanti; Budi Susetyo; Gerry Alfa Dito
Journal of Mathematics, Computations and Statistics Vol. 9 No. 1 (2026): Volume 09 Issue 01 (March 2026)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/xyyv0f37

Abstract

Abstract. Poverty is a major socioeconomic challenge in Indonesia that affects the effectiveness of social protection programs. In response to this challenge, the government has created social assistance programs to improve the welfare of the people. However, the distribution of social assistance is often considered to be inaccurate, resulting in households that are deemed eligible for social assistance not being identified as recipients. One solution to improve the accuracy of distribution is the application of machine learning in the context of classification. Several tree-based models, such as LightGBM, Random Forest, and XGBoost, were selected because of their superior capabilities compared to classical models such as logistic regression, especially in handling complex data and fulfilling model assumptions. This study compares the performance of these three models in predicting social assistance recipient status using data from the 2024 West Java Provincial National Socioeconomic Survey (SUSENAS). Model evaluation was conducted on several data pre-processing scenarios involving outlier handling, class balancing, and feature engineering. The results show that LightGBM consistently outperforms the other models on six metrics, namely Accuracy, Balanced Accuracy, F1-Score, ROC-AUC, PR-AUC, and Brier Score, out of a total of eight evaluation metrics used. SHAP analysis identifies Social Assistance History and Asset Score as the most influential features for model prediction. Friedman and Nemenyi nonparametric tests confirmed significant performance differences between LightGBM and other models based on the F1-Score, PR-AUC, and Brier Score metrics. These findings indicate that tree-based models, particularly LightGBM, can support the development of a more targeted and data-driven social assistance targeting system. Keywords: Social Assistance; Tree-Based; SHAP; SUSENAS; Hybrid Bayesian Optimization
Technical Analysis of the Indonesian Stock Market with Gated Recurrent Unit and Temporal Convolutional Network Siti Aisyah; Yenni Angraini; Kusman Sadik; Bagus Sartono; Gerry Alfa Dito
JUITA: Jurnal Informatika JUITA Vol. 12 No. 2, November 2024
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/juita.v12i2.23464

Abstract

Big data is essential in the age of 4.0 industry as it becomes the basis of decision making. Deep learning research in the last few years has been proven effective in understanding complex big data patterns, especially in the finance sector. The rapid growth of the Indonesian stock market in the last 20 years, which was driven by globalization, prompted fluctuation in the Bursa Efek Jakarta (JKSE) which was influenced by stock prices, commodity prices, and exchange rate. This study identifies the main indicators of Indonesian stock market crisis, applies and compares deep learning models, particularly Gated Recurrent Unit (GRU) and Temporal Convolutional Network (TCN), in predicting stock prices. This study identified 20 JKSE crisis points between the 2002-2023 period with average return value at around -6%. All variables correlated positively with JKSE, with SET.BK as the highest correlated variable in lag 0. The American and European stock market, commodity price, and exchange rate tend to show a pattern opposite to the JKSE crisis. Predictor variables such as STI, HIS, KLSE, KS11, SET.BK, PSEI.PS, RUT, and USDIDR are chosen based on significant cross correlation and average return plot. Hyperparameter tuning and cross validation within a 3 years window concluded that the GRU model is accurate and efficient, with RMSE value at 43.35568 and MAE value at 33.66909 in the validation data.
Performance Analysis of Tree-Based Models for Classifying Complete Basic Childhood Immunization in West Java Windi Pangesti; Mega Maulina; Hazelita Dwi Rahmasari; Bagus Sartono; Budi Susetyo; Aulia Rizki Firdawanti; Gerry Alfa Dito
Inferensi Vol 9 No 1 (2026)
Publisher : Department of Statistics ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j27213862.v9i1.9167

Abstract

Complete basic immunization is a key public health indicator, and disparities in coverage remain a major concern in West Java. The 2024 Universal Child Immunization (UCI) rate in West Java reached only 77.47%, declining from 2023 and reflecting persistent disparities in access to immunization services, particularly between urban and rural areas. This study aims to identify the determinants of complete basic immunization among children in West Java using SUSENAS 2024 survey data (n = 4,672). Three tree- based classification algorithms CART, Random Forest, and LightGBM were applied, with class imbalance addressed using SMOTE, Tomek Links, and the SMOTE–Tomek Links hybrid method. Model performance was evaluated using balanced accuracy. The Random Forest model combined with SMOTE achieved the highest performance, with a balanced accuracy of 60.3% and an overall accuracy of 70.3%. This model also demonstrated superior capability in identifying children with incomplete immunization. Global feature importance results indicate that household spending category, KIA book ownership, maternal age at first birth, and maternal education are the strongest predictors of complete basic immunization. SHAP analysis reveals contrasting patterns: knowledge- based factors dominate in urban areas, while structural and socioeconomic constraints are more influential in rural areas. These findings underscore the importance of geographically targeted immunization strategies to support equitable access across urban and rural communities in West Java.
Evaluasi Perbandingan Model XGBoost, Random Forest, LightGBM, dan Artificial Neural Network dalam Klasifikasi Kerawanan Pangan Mardatunnisa Isnaini; Dela Gustiara; Rizqi Annafi Muhadi; Shalshabilla Shafa; Bagus Sartono; Aulia Rizki Firdawanti; Budi Susetyo; Gerry Alfa Dito
Euler : Jurnal Ilmiah Matematika, Sains dan Teknologi Volume 14 Issue 1 April 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/euler.v14i1.36227

Abstract

Food insecurity remains a serious household-level issue, particularly in densely populated regions such as West Java, highlighting the need for analytical approaches capable of accurately identifying vulnerable groups. Machine learning algorithms offer the potential to improve the accuracy and precision of food insecurity classification based on survey data. This study aims to compare the predictive performance and variable importance identification of four machine learning algorithms—Random Forest, Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN)—in predicting household food insecurity status. The analysis employs SUSENAS 2023 data covering 26,012 households with 14 predictor variables, and food insecurity is classified using the Food Insecurity Experience Scale (FIES). Class imbalance is addressed using the Synthetic Minority Over-sampling Technique (SMOTE) within a 10-fold cross-validation framework. The results show that XGBoost achieves the highest accuracy of 71%, while Random Forest provides the best balanced accuracy under the SMOTE scenario. Moreover, all algorithms consistently identify the Wealth Index as the most influential predictor based on their respective Variable Importance measures, followed by variables related to water access and food assistance. Accordingly, XGBoost is recommended in terms of accuracy, whereas Random Forest demonstrates superior balanced accuracy and prediction stability.
IndoBERT Optimization for Sentiment Analysis on DeepSeek App Reviews Muh. Sunan; Unique Desyrre A. Resiloy; Desy Endriani; Cici Suhaeni; Bagus Sartono; Gerry Alfa Dito
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 20, No 1 (2026): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.107507

Abstract

In the digital era, sentiment analysis is important to evaluate public opinion, especially in the context of Play Store apps with Indonesian-language reviews. This research aims to improve the performance of the IndoBERT model in sentiment analysis of DeepSeek app reviews by using data augmentation and hyperparameter tuning techniques. Data augmentation is done through the back-translation technique, while the hyperparameters tested include the number of epochs, learning rate, and batch size. Experimental results show that the combination of data augmentation with epoch 10, learning rate 2e-5, and batch size 16 produces the highest accuracy of 93.95% and F1-score of 0.94, with better stability than the model without augmentation. The model without augmentation showed fluctuations in performance, indicating overfitting in some configurations. These findings confirm the importance of applying augmentation techniques and hyperparameter tuning in improving the accuracy and stability of sentiment analysis models, and contribute to the development of NLP models for Indonesian and other resource-constrained languages.
Co-Authors Aulia Rizki Firdawanti Bagus Sartono Budi Susetyo Carlya Agmis Aimandiga Cici Suhaeni Dela Gustiara Desy Endriani Hazelita Dwi Rahmasari I Gusti Ngurah Sentana Putra Kusman Sadik Mardatunnisa Isnaini Mega Maulina Muh. Sunan Muhammad Syafiq Rizqi Annafi Muhadi Shalshabilla Shafa Siti Aisyah Syella Zignora Limba Unique Desyrre A. Resiloy Wawan Saputra Windi Pangesti Yani Prihantini Hiola Yenni Angraini Zulhijrah