Claim Missing Document
Check
Articles

Found 7 Documents
Search
Journal : The Indonesian Journal of Computer Science

Measuring mobile banking service quality using Topic Modeling and Term Ranking: A case study of an Indonesian digital bank Anggraini, Veny; Budi, Indra; Santoso, Aris Budi; Putra, Prabu Kresna
The Indonesian Journal of Computer Science Vol. 13 No. 6 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i6.4517

Abstract

The rapid expansion of digital transactions in Indonesia is driving the transformation of both traditional and digital banks. Since digital banks operate without physical branches, all banking services are via mobile banking apps. This study examines mobile banking service quality using text mining techniques like topic modeling and term ranking to analyze 11,815 user reviews from app stores and assess customer satisfaction through ratings. The research involves extracting and preprocessing reviews, identifying key topics, and linking them to satisfaction levels. Seven service dimensions were found: customers were satisfied with Enjoyment, Debit Card Delivery, and Feature-Free Transactions but dissatisfied with Accessibility, Data Privacy, Loan Services, and Touchless Customer Support. Debit Card Delivery and Feature-Free Transactions were highlighted as significant factors in Indonesia's digital banking market. With limitations in analyzing user reviews in Bahasa Indonesia, the findings are specific to the Indonesian digital banking context and may not be applicable elsewhere.
Leveraging LSTM Predictions for Enhanced Portfolio Allocation with Markowitz Mean-Variance Optimization Sahid, Irfanda Husni; Budi, Indra
The Indonesian Journal of Computer Science Vol. 13 No. 6 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i6.4573

Abstract

This research investigates the application of Long Short-Term Memory (LSTM) networks for predicting expected returns and integrating these predictions into the Markowitz Mean-Variance Optimization (MVO) framework. The study utilized historical data from eight Indonesian stocks: BBCA, BBRI, TLKM, EXCL, UNVR, ICBP, ASII, and SMGR. The dataset covered the period from 2018 to 2024. The LSTM model was employed to predict cumulative returns over a 90-day horizon, and its performance was compared to the Exponentially Weighted Moving Average (EWMA) method. The findings indicate that LSTM achieved lower Root Mean Squared Error (RMSE) than EWMA for four stocks (BBCA, BBRI, UNVR, ICBP), while EWMA demonstrated better performance for the remaining four stocks. MVO results revealed that LSTM-based predictions achieved an average return of 4.285%, surpassing EWMA's 1.856% but falling short of the 12.298% obtained using actual returns. These results highlight the potential of LSTM models to enhance portfolio allocation strategies.
Optimizing Climate Forecasts Across 16 Zones Using Regression-Based Machine Learning Models Ardin; Budi, Indra
The Indonesian Journal of Computer Science Vol. 14 No. 1 (2025): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i1.4593

Abstract

The XYZ Climatology Station faces challenges in improving the accuracy of decadal rainfall forecasts, with an average achievement of 57.4% in 2022 and 58.8% in 2023, below the organizational performance target of 70% accuracy as set in its strategic objectives. This study aims to develop machine learning-based predictive models for 16 climate zones to enhance forecast accuracy. Five regression algorithms—Multiple Linear Regression, Support Vector Regression, Extra Trees Regression, Random Forest Regression, and Decision Tree Regression—were tested under two scenarios: input variable variations (VR) and time series data length (TS). Results showed that the VR scenario increased average accuracy to 71.7% (2022) and 69.4% (2023), while the TS scenario achieved 73.1% (2022) and 72.6% (2023). Support Vector Regression and Extra Trees Regression demonstrated the best performance in most zones. These models are expected to be operationalized to improve climatological information services and better meet public and stakeholder needs.
Analisis Sentimen Berbasis Aspek Aplikasi Brimo berdasarkan Ulasan Pengguna di Google Playstore Azarya, Yosia; Budi, Indra
The Indonesian Journal of Computer Science Vol. 14 No. 1 (2025): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i1.4613

Abstract

BRI is focused through their mobile banking superapp known as BRImo. However, based on discussions with the BRImo application research team, The user reviews available on the Google Play Store application service page could be classified based on the PACMAD usability aspects and sentiment using several classification models, including Random Forest, Decision Tree, and Extreme Gradient Boosting, with TF-IDF employed as the feature extraction method. Additionally, the Random Oversampling and Synthetic Minority Oversampling Technique (SMOTE) methods were applied as supplementary treatments to address the issue of imbalanced classes in BRImo application user review data. Topic modeling was also conducted using the LDA method to identify keywords and the main discussion topics for each PACMAD usability aspect and its sentiment, resulting in clear topics that can serve as a focus for the development of the BRImo application. The research findings indicate that the XGBoost classification model, combined with the SMOTE sampling method, demonstrated the best performance in classifying PACMAD usability aspects and sentiments, achieving F1-scores of 86.55% and 89.59%, respectively. Furthermore, the key topics for each PACMAD usability aspect and their associated sentiments were identified.
Dinamika Opini Publik Indonesia terhadap Krisis Rohingya dalam Perspektif Waktu menggunakan Traditional Machine Learning dan Deep Learning Istiqomah, Relaci Aprilia; Budi, Indra
The Indonesian Journal of Computer Science Vol. 13 No. 3 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i3.4069

Abstract

The Rohingya are an ethnic minority who currently still face persecution and discrimination in Myanmar, so they have to flee to neighboring countries, such as Indonesia. However, the polemic regarding the issue of the existence of Rohingya refugees in Indonesia still shows that there are differences of opinion between groups who support and oppose it. For this reason, this research aims to determine the dynamics of Indonesian public opinion regarding the Rohingya from 2015-2023 via Twitter, as well as find out the topics that are often discussed each year using LDA. This research compares classification methods using traditional machine learning algorithms (NB, SVM, LR, and DT) and deep learning algorithms (LSTM, GRU, LSTM-GRU, and GRU-LSTM). The research results show that the traditional machine learning algorithm, LR, has the highest accuracy. There has been a change in sentiment from initially being dominated by positive sentiment to negative sentiment which is more dominant in the last five years. The topics that are often discussed for positive sentiment are the support of the Indonesian people for the Rohingya in providing assistance and shelter, while the negative topics are related to concerns about the social, economic, and security impacts that may be caused by the presence of Rohingya refugees.
Uncovering the Reasons Behind Abstain Voters' Stances in the 2024 Indonesian Presidential Election: Social Media X Study Cases Putri, Irzanes; Insani, Faiz Nur Fitrah; Budi, Indra; Santoso, Aris Budi; Putra, Prabu Kresna
The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i4.4126

Abstract

The Indonesian Government expects the participation of all Indonesian people in holding General Elections. However, according to the 2019 Political Statistics by BPS, there were 34.75 million people who did not exercise their right to vote or were abstain voters (golput) in the 2019 Election. This research aims to analyze individual attitudes towards abstaining voters using stance analysis and topic modelling. From 9,045 collected tweets, subsequent manual annotation revealed 2,566 pro stances, 5,264 neutral stances, and 1,215 contra stances. The classification models utilized are Random Forest, Decision Tree, Logistic Regression, Support Vector Machine, K-Nearest Neighbor, and Gradient Boosting. The classification outcomes will be analyzed by comparing the accuracy, precision, recall, and F1-score results based on their algorithms and n-grams. The results obtained from the stance analysis show that Random Forest achieved the highest accuracy and precision scores, with values of 84% and 83%, respectively. The discussion topic among those supporting golput due to low trust in the presidential and vice-presidential candidates. Other topics mentioned public feels dissatisfied with the pairs of candidates.
Perbandingan Random Search dan Algoritma Genetika dalam Penyetelan Hyperparameter XGBoost pada Retail Sales Forecasting Tiastama, Sheren Afryan; Budi, Indra
The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i4.4285

Abstract

Sales is part of the important factor that influences a company in determining two things, namely profits and losses on the company. The right strategy to determine the amount of sales can be done through forecasting. Therefore, sales forecasting requires the right technique to produce accurate results. Machine learning has been proven to help overcome sales forecasting, one of which is XGBoost. However, XGBoost has many hyperparameters that affect its performance, it requires a hyperparameter setting method to produce an optimal hyperparameter. Random searches and genetic algorithms are optimized methods to find the optimal hyperparameter on XGBoost. The two methods of optimization were compared in this study with the measurement of RMSE performance in doing retail sales forecasting on the sales data of the retail company Rossmann Store which comes from the Kaggle site. The research obtained random search results superior to the genetic algorithm with RMSE values on the training process and the testing process are 0.123 and 0.122. Meanwhile, the RMSE values generated by genetic algorithms in the training and testing process are 0.333 and 0.332.