cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
-
Journal Mail Official
jurnal.bits@gmail.com
Editorial Address
-
Location
Kota medan,
Sumatera utara
INDONESIA
Building of Informatics, Technology and Science
Published by Forum Kerjasama Pendidikan TInggi
ISSN : 26848910     EISSN : 26853310     DOI : -
Core Subject : Science,
Computer Science & IT
Building of Informatics, Technology and Science (BITS) is an open access media in publishing scientific articles that contain the results of research in information technology and computers. Paper that enters this journal will be checked for plagiarism and peer-rewiew first to maintain its quality. This journal is managed by Forum Kerjasama Pendidikan Tinggi (FKPT) published 2 times a year in Juni and Desember. The existence of this journal is expected to develop research and make a real contribution in improving research resources in the field of information technology and computers.
Arjuna Subject : -
Articles 926 Documents
 82   83   84   85   86 
Sistem Pendukung Keputusan Pemberian Kredit pada Koperasi Simpan Pinjam Menggunakan Algoritma Simple Additive Weighting (SAW) dengan Pembobotan Entropy Afnita, Afnita; Masrizal, Masrizal; Irmayani, Deci
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7385

Abstract

The credit granting process in savings and loan cooperatives often faces obstacles in terms of objectivity and efficiency of assessment of prospective debtors. Manual and subjective assessments have the potential to result in inaccurate decisions and increase the risk of problematic credit. This study aims to develop a Decision Support System (DSS) in credit granting by implementing the Simple Additive Weighting (SAW) algorithm combined with the Entropy weighting method. The SAW method was chosen because of its ability to calculate aggregate values ​​against a number of criteria, while the Entropy method is used to determine the weight of the criteria objectively based on data variations. The criteria used include monthly income, credit history, number of dependents, length of membership, and history of installment ratio to income. The results of the study showed that the system was able to systematically sort 15 alternative customers. Based on the final calculation results, the customer who obtained the highest score of 0.862 and was ranked first as the best candidate for credit recipients. These results indicate that the SAW method with Entropy weighting can provide objective recommendations and help make more appropriate decisions in granting credit. The main contribution of this research is to provide a technology-based tool that can improve accuracy, transparency, and efficiency in the creditworthiness evaluation process in savings and loan cooperatives.
Analisis Faktor-Faktor yang Mempengaruhi Tingkat Kelulusan Siswa Menggunakan Algoritma KNN Sianipar, Vitasari; Irmayani, Deci; Bangun, Budianto
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7386

Abstract

Student graduation rates are influenced by various academic and non-academic factors, making it necessary to develop analytical methods to classify students based on their likelihood of graduation. This study applies the K-Nearest Neighbors (KNN) algorithm to analyze the factors affecting student graduation at SD Negeri 112269 Padang Lais. The KNN algorithm works by calculating the Euclidean distance between the tested student data and other student data, then determining the graduation status based on the majority of the K nearest neighbors. The results indicate that using K=5 produces highly accurate classifications with an accuracy rate of 100%, where students with the smallest distance to those who have graduated are more likely to pass. The contribution of this study is to demonstrate that the KNN method can serve as a decision-support tool for predicting student graduation and provide insights into the use of classification algorithms in educational decision-making. Future research can enhance the model by incorporating more diverse variables and testing it on larger datasets to improve prediction generalization.
Prediksi Kinerja Akademik Siswa Bimbingan Belajar Menggunakan Algoritma Extreme Gradient Boosting (XGBoost) Alfarizi, Muhammad Bayu Ardi; Witanti, Wina; Komarudin, Agus
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7387

Abstract

Improving the quality of education has become a primary focus in addressing the increasingly complex challenges of the educational landscape. One promising approach to support data-driven decision-making is the prediction of students' academic performance using machine learning algorithms. This study aims to develop a classification model for predicting students' academic performance by leveraging the Extreme Gradient Boosting (XGBoost) algorithm. The dataset used was obtained from SMPN 1 Gunung Halu and includes both academic and non-academic attributes of students. Five key features were selected: initial grades, midterm grades, final grades, student behavior, and attendance. Data preprocessing involved feature selection, handling missing values, transforming categorical variables using label encoding, and balancing the classes using the SMOTE method. The XGBoost model was then trained using an 80:20 data split and hyperparameter tuning was performed using Grid Search. Evaluation results showed that the model achieved an accuracy of 84% with balanced F1-scores across all classes. The model outperformed other algorithms such as Bagging and Random Forest. With its strong accuracy and stability, the XGBoost model has the potential to serve as a tool for identifying students who require academic intervention. This study makes a significant contribution to the development of AI-based education systems and provides a foundation for the application of machine learning in improving the quality of secondary-level learning.
Perbandingan Algoritma Support Vector Machine dan Bi-Directional Long Short Term Memory Dalam Mengklasifikasi Berita Hoaks Merinda, Siska; Ciksadan, Ciksadan; Fadhli, Mohammad
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7391

Abstract

The rapid advancement of digital technology has made it easier to spread information widely and quickly. However, this ease of access has also contributed to the rise of false or misleading news, commonly known as hoaxes, which can confuse the public. This study aims to evaluate and compare the performance of two machine learning algorithms, namely Support Vector Machine (SVM) and Bi-Directional Long Short Term Memory (BiLSTM), in classifying hoax news written in Indonesian. The research adopts a supervised learning approach, where models are trained using pre-labeled data categorized as either hoax or non-hoax. The process begins with collecting data from trusted sources, followed by several preprocessing steps, including text cleaning, tokenization, stopword removal, and stemming. After preprocessing, the dataset is split into training and testing sets in an 80:20 ratio. The results show that the SVM model achieved an accuracy of 98.46%, with 98% precision and 99% recall for the non-hoax category. In comparison, the BiLSTM model performed better, reaching 99% accuracy, with both precision and recall at 99% for both categories. These findings indicate that BiLSTM is more effective at capturing linguistic context and identifying patterns in hoax-related content. Additionally, the models were implemented into a web-based system to assess their real-world detection capabilities.
Market Potential Analysis Based on Population and Land Area using K-Means Clustering and MCDM Approaches Arfyanti, Ita; Bustomi, Tommy; Haristyawan, Ivan
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7392

Abstract

In an increasingly competitive global market, accurately identifying untapped market potential in small to medium-sized regions, often overlooked by traditional single-indicator analyses, presents a significant challenge for strategic decision-making. This study addresses this by proposing a hybrid analytical framework integrating K-Means Clustering with Multi-Criteria Decision-Making (MCDM) methods, utilizing population size and land area as core indicators. The primary objective is to develop a robust market potential analysis model capable of systematically classifying regions and providing actionable insights for resource optimization and market expansion. The methodology involves determining the optimal number of clusters using the elbow method (k=3, with a silhouette score of 0.8862), followed by K-Means clustering to segment Asian countries into distinct groups. Subsequently, three MCDM methods SAW, WP, and WASPAS are applied to rank countries within the most relevant cluster (low population and area) under various weighting scenarios. The results consistently demonstrate Turkey's top ranking across all MCDM methods, highlighting its robust market potential regardless of weight variations. Crucially, a very strong agreement in rankings between the MCDM methods was observed, evidenced by Spearman's correlation coefficients consistently above 0.98, with the highest correlation between SAW and WASPAS (0.998379 for [0.3, 0.7] weights). This high correlation confirms the reliability and consistency of the model, concluding that SAW and WASPAS are highly suitable for this analysis, and identifying Turkey as the leading country in market potential among 50 Asian nations based on the criteria studied.
Penentuan Siswa Berprestasi Menggunakan Metode Analytical Hierarchy Process (AHP) dengan Pembobotan Entropy dalam Sistem Pendukung Keputusan Sudarman, Dita Auliya; Irmayani, Deci; Masrizal, Masrizal; Ritonga, Ali Akbar
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7393

Abstract

Determining outstanding students is one of the important aspects in the world of education to provide objective awards to students who have the best academic and non-academic achievements. This study aims to develop a decision support system (DSS) in determining outstanding students using the Analytical Hierarchy Process (AHP) method with Entropy weighting. The AHP method is used to determine the weight of the criteria based on pairwise comparisons, while the Entropy method is used to balance the weight based on data distribution. The results of the calculations in the system show that the alternative with the highest value is Habibi Altaqi (A18) with a value of 89,078, followed by Alif Alhafiz Syahputra (A25) and Sintya Azahra (A03) in second and third place. Conversely, the alternative with the lowest value is Eka (A10) with a value of 73,554, ranked 25th. The results of this study indicate that the AHP and Entropy methods are able to provide objective and systematic evaluations in the selection process of outstanding students. The system developed can be used as a tool for schools in making decisions more accurately and transparently. The contribution of this research is to provide an integrated approach between AHP and Entropy in a decision support system that can be adopted by other educational institutions to improve objectivity and accountability in the assessment process of high-achieving students.
Sistem Pendukung Keputusan untuk Kelayakan Kredit Berdasarkan Profil Keuangan Menggunakan Metode TOPSIS Fitriani, Sinta; Masrizal, Masrizal; Irmayani, Deci
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7394

Abstract

Decision Support System (DSS) is one of the essential tools in assisting complex decision-making processes, including creditworthiness assessment based on customers’ financial profiles. This study aims to design a DSS capable of evaluating credit eligibility more accurately, objectively, and efficiently by applying the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method. This method is used to rank customer alternatives based on their proximity to an ideal solution by considering several criteria such as income, expenses, collateral, and credit history. The data used in this research were obtained from customer financial datasets containing information related to their financial profiles. The system was tested using simulation data, and the results showed that the TOPSIS method can provide creditworthiness evaluations with a high level of accuracy while reducing time and errors compared to manual assessment methods. The final research results identified the best alternative as A3 with a score of 0.8859, indicating the most optimal credit eligibility level. These findings are expected to serve as a valuable reference for financial institutions in making credit approval decisions, improving transparency, and minimizing risks in the credit process. The implementation of the TOPSIS method has proven to be an effective approach in supporting data-driven decision-making.
Determining the Best E-Commerce Using the Multi Criteria Decision Making (MCDM) Method Salmon, Salmon; Lailiyah, Siti; Arriyanti, Eka
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7395

Abstract

The rapid expansion of e-commerce has positively influenced lifestyles and fueled economic growth, as evidenced by rising transaction volumes and government revenue. However, challenges persist, especially in consumer security, logistics infrastructure, and taxation. The quality of e-commerce websites is crucial, serving as a primary source of customer information and ensuring secure transactions. Selecting the right e-commerce platform is also essential for business development. Despite the proliferation of e-commerce platforms offering diverse features and user-friendly interfaces, issues like product quality discrepancies, fraudulent activities, and incomplete features continue to frustrate consumers. To address these challenges and aid consumers in selecting optimal platforms, Multi-Criteria Decision Making (MCDM) methods are employed. This study explores various MCDM techniques to rank 8 major e-commerce platforms based on 5 criteria. The analysis consistently identifies Shopee as the top-performing platform. While Tokopedia, Bukalapak, Lazada, and TikTok Shop show some variations in rankings depending on the MCDM method used, Blibli, JD.ID, and OLX Indonesia maintain consistent rankings across all methods. This suggests that while Shopee demonstrates clear superiority, the subtle differences in MCDM methodologies can influence the relative rankings of other platforms.
Analisis Perbandingan Metode Artificial Neural Network dan XGBoost untuk Prediksi Profit dari Data Transaksi Point of Sale Kurniawan, Panji; Setyaningsih, Putry Wahyu
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7399

Abstract

In the business world, profit is a key indicator of a company’s success, and predicting future profit is essential for strategic decision-making, such as inventory planning, pricing strategies, and marketing efforts. However, market fluctuations and dynamic consumer behavior often make profit prediction a significant challenge. With technological advancements, data mining methods have become increasingly utilized for analyzing such complex datasets, including Artificial Neural Networks (ANN) and XGBoost. This study explicitly aims to compare the performance of ANN and XGBoost in predicting profit based on transactional data from a Point of Sale (POS) system. ANN was selected for its ability to learn intricate and non-linear patterns in data, while XGBoost is known for its efficiency in processing large datasets and preventing overfitting through boosting and regularization techniques. The dataset consists of 44,348 transactions, with 80% used for training and 20% for testing. Results show that the ANN model achieved an R² of 0.9996 and a MAE of 1,359, outperforming the XGBoost model, which obtained an R² of 0.9978 and a MAE of 1,600. This significant difference indicates that ANN delivers more accurate predictions. ANN’s advantage lies in its capacity to develop complex internal representations of data, making it more responsive to subtle patterns in transactional behavior. These findings highlight the importance of choosing the appropriate model for profit prediction and demonstrate that ANN provides superior predictive accuracy, supporting more precise and data-driven strategic decisions for financial and sales management..
Klasifikasi Jenis Bunga Iris Berdasarkan Fitur Morfologi Menggunakan Algoritma Naive Bayes Sari, Ely Novita; Irmayani, Deci; Bangun, Budianto
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7401

Abstract

This study aims to classify the types of Iris flowers based on morphological features using the Naive Bayes algorithm. Iris flowers consist of three types, namely Iris-Setosa, Iris-Versicolor, and Iris-Virginica, which can be distinguished based on the length and width of the petals as well as the length and width of the sepals. The dataset used in this research is the Iris dataset, which contains information on four morphological features from these three types of flowers. The Naive Bayes algorithm was chosen because of its advantages in performing probability-based classification in a simple, fast, and effective manner, especially for data with independent features. The research stages include data collection, feature extraction, splitting the data into training and testing sets, training the model using the Naive Bayes algorithm, and testing the model to evaluate classification accuracy. The results of the study show that the Naive Bayes model is able to classify the test data accurately, with the highest probability value obtained in the Iris-Versicolor class, with a value of P(Versicolor│X)=1. This indicates that the test data has the highest similarity to that species compared to the other two species. Thus, the Naive Bayes algorithm proves effective for classifying types of Iris flowers based on their morphological features.

Page 84 of 93 | Total Record : 926

 82   83   84   85   86 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol 7 No 3 (2025): December 2025 Vol 7 No 2 (2025): September 2025 Vol 7 No 1 (2025): June (2025) Vol 6 No 4 (2025): March 2025 Vol 6 No 3 (2024): December 2024 Vol 6 No 2 (2024): September 2024 Vol 6 No 1 (2024): June 2024 Vol 5 No 4 (2024): March 2024 Vol 5 No 3 (2023): December 2023 Vol 5 No 2 (2023): September 2023 Vol 5 No 1 (2023): June 2023 Vol 4 No 4 (2023): March 2023 Vol 4 No 3 (2022): December 2022 Vol 4 No 2 (2022): September 2022 Vol 4 No 1 (2022): June 2022 Vol 3 No 4 (2022): March 2022 Vol 3 No 3 (2021): December 2021 Vol 3 No 2 (2021): September 2021 Vol 3 No 1 (2021): June 2021 Vol 2 No 2 (2020): December 2020 Vol 2 No 1 (2020): June 2020 Vol 1 No 2 (2019): December 2019 Vol 1 No 1 (2019): June 2019 Vol 1 No 1 (2019): Edisi Juni More Issue