cover
Contact Name
Husni Teja Sukmana
Contact Email
husni@bright-journal.org
Phone
+62895422720524
Journal Mail Official
jads@bright-journal.org
Editorial Address
Gedung FST UIN Jakarta, Jl. Lkr. Kampus UIN, Cemp. Putih, Kec. Ciputat Tim., Kota Tangerang Selatan, Banten 15412
Location
Kota adm. jakarta pusat,
Dki jakarta
INDONESIA
Journal of Applied Data Sciences
Published by Bright Publisher
ISSN : -     EISSN : 27236471     DOI : doi.org/10.47738/jads
One of the current hot topics in science is data: how can datasets be used in scientific and scholarly research in a more reliable, citable and accountable way? Data is of paramount importance to scientific progress, yet most research data remains private. Enhancing the transparency of the processes applied to collect, treat and analyze data will help to render scientific research results reproducible and thus more accountable. The datasets itself should also be accessible to other researchers, so that research publications, dataset descriptions, and the actual datasets can be linked. The journal Data provides a forum to publish methodical papers on processes applied to data collection, treatment and analysis, as well as for data descriptors publishing descriptions of a linked dataset.
Articles 1,270 Documents
Implementation of Blended Learning System in Higher Education to Explore the Interaction of Technology, Organization, Environment, and Technology Acceptance Model Nur Aeni Hidayah; Qurrotul Aini; Putri Ghania
Journal of Applied Data Sciences Vol 5, No 2: MAY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i2.204

Abstract

A thorough examination of the deployment of blended learning after the COVID-19 pandemic is necessary to ensure its efficacy in enhancing the educational quality in higher education. The objective of this study is to identify the key elements that strongly impact the adoption of a blended learning system. It will be achieved by applying both the technology-organization-environment framework and the technology acceptance model. The study formulated eight hypotheses and administered online surveys on social media platforms to gather data from a total of 249 participants from four Islamic state universities. Analyzed data with the PLS methodology. The findings indicated that 92% of participants concurred that blended learning enhanced the quality of education. In addition, seven assumptions have been accepted, with the relationship between the technology context and the perceived ease of use in the blended learning system being the most relevant component. On the other hand, the PLS prediction results demonstrate that the suggested model possesses moderate predictive capability, as evidenced by its lower RMSE and MAE values in comparison to the linear regression model. Subsequent investigations should focus on analyzing the four blended learning models while taking into account factors such as teacher competence, educational systems, and social impacts.
Data Visualization of Climate Patterns in Indonesia Using Python and Looker Studio Dashboard: A Visual Data Mining Approach Rina Refianti; Achmad Benny Mutiara; Ananda Satria Ariyanto
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.420

Abstract

Climate has a significant impact on the lives of Indonesian people. Information about climate patterns, when presented visually and interactively, can greatly enhance understanding of climate conditions in Indonesia. This study aims to produce a visualization of climate pattern data in Indonesia that can be accessed online by the general public, serving as a valuable resource for climate information. The study highlights the ability to display historical trends for a 10-year period (2010-2020) through interactive visuals, which load information according to user-defined filters, enabling diverse presentations of data. The research employs the Visual Data Mining method, encompassing Project Planning, Data Preparation, and Data Analysis phases. Additionally, Exploratory Data Analysis techniques were utilized in the data analysis phase. The data was cleaned and processed using the Python programming language with libraries such as pandas, numpy, seaborn, and matplotlib. Visualizations were created using Looker Studio tools and published on a website, providing accessible climate pattern information in Indonesia via the Internet. The final results of this research indicate that the developed climate visualization dashboard successfully delivers detailed insights into sunlight duration, temperature, humidity, rainfall, and wind speed across various Indonesian regions. Users can effectively monitor climate trends and weather changes. The dashboard also demonstrates significant seasonal variations and differences in climate patterns between provinces. Performance metrics reveal that the dashboard meets Key Performance Indicators, achieving a click-through ratio of 40.1%, the average page position in search engines is 4.8 top positions, and receiving positive user experience scores. Further development and research on the Climate Pattern Dashboard in Indonesia still have room for enhancement. Important aspects include expanding data coverage to include multiple decades for observing significant climate patterns and applying sophisticated prediction methods like machine learning algorithms for future climate change projections.
Feature Selection Methods as Attribute Weighting Schemes for Clustering Corporate Financial Statements Tora Fahrudin; Dedy Rahman Wijaya
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1410

Abstract

Financial clustering plays an important role in uncovering hidden patterns and supporting decision-making in high-dimensional financial statement analysis. However, clustering performance is often constrained by noisy, redundant, and heterogeneous attributes that reduce cluster quality, interpretability, and robustness. Although previous studies in financial analytics have extensively explored clustering algorithms, limited attention has been given to systematically evaluating feature-selection-based attribute weighting strategies for improving clustering effectiveness in complex financial datasets. This study investigates the effectiveness of 6 feature-selection-based weighting strategies for improving financial statement clustering using annual financial data from 604 publicly listed companies on the Indonesia Stock Exchange during 2020-2023. Rather than relying solely on feature filtering, the evaluated methods were utilized to prioritize informative financial attributes and improve clustering structure. Clustering performance was assessed using internal validation metrics, including the Silhouette Coefficient, Dunn Index, Calinski Harabasz Score, and Davies Bouldin Index to evaluate cluster compactness, separation, and overall quality. The results demonstrate that feature-selection-based weighting substantially improves clustering quality compared with the baseline. Fisher Score achieved the strongest overall performance with a Silhouette score of 0.9899, Dunn Index of 1.7238, and Davies Bouldin Index of 0.0034, outperforming the baseline values of 0.8678, 0.3509, and 0.8716, respectively. Autoencoder-based ranking also produced highly competitive results, achieving a Silhouette score of 0.9757 and a Calinski Harabasz Index of 37,105.45. These findings indicate that prioritizing informative financial attributes significantly enhances cluster compactness, separation, and interpretability. The study contributes a comprehensive comparative evaluation of feature-selection-based weighting schemes and provides practical insights for financial segmentation, risk profiling, decision support, and data-driven financial analytics. This study further offers a foundation for developing more robust clustering frameworks for complex financial datasets.
An Ensemble and Filtering-Based System for Predicting Educational Data Mining Andhika Rafi Hananto; Silvia Anggun Rahayu; Taqwa Hariguna
Journal of Applied Data Sciences Vol 2, No 4: DECEMBER 2021
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v2i4.44

Abstract

When developing a prediction paradigm, an ensemble technique such as boosting is used. It is built on a heuristic framework. Generally speaking, engineering ensemble learning is more accurate than individual classifiers when it comes to making predictions. Consequently, numerous ensemble strategies have been presented in this work, particularly to provide a more complete understanding of the essential methods in general. Researchers have experimented with boosting methods to forecast student performance as part of a variety of ensemble techniques. The researchers employed improvement approaches to construct an accurate predictive educational model, which was based on a key phenomena seen in categorization and prediction operations. In light of the uniqueness and originality of the suggested strategy in educational data mining, the researchers used augmentation strategies in order to construct an accurate predictive pedagogical model. Tenfold cross-validation was performed to evaluate the effectiveness of the basic classifiers, which included the random tree, the j48, the knn, and the Naive Bayes. The random tree was found to be the most effective classifier. Several additional screening techniques, including oversampling (SMOTE) and undersampling (Spread subsampling), were utilized to analyze any statistically significant variations in results between the meta and base classifiers that had been identified between the meta and base classifiers. The use of ensemble and screening strategies, as compared to the use of standard classifiers, has demonstrated considerable gains in predicting student performance, as has the use of either strategy alone. Furthermore, after the completion of a performance research on each approach, two new prediction models have been established on the basis of the improved results gained thus far.
Development of a Self-Identity Construction Model for Private Vocational College Students Using Data Science Techniques Mei Chen; Thosporn Sangsawang
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.731

Abstract

This study aimed to synthesize theories of self-identity learning to develop a self-identity development model for private vocational college students in Yunnan Province, China, identify key influencing factors, and evaluate the model's effectiveness. Using purposive sampling, the study involved 17 experts and 1,004 first-year students. Data were collected through a semi-structured questionnaire via Delphi Technique, supported by consultations via email, WeChat video, and in-person interviews. The model’s validity was assessed based on satisfaction levels from students, teachers, and stakeholders. Statistical analyses included weight calculations, means, standard deviations, coefficients of variation, and path analysis. The results showed strong expert consensus, with an average score of M = 4.5008 and CV = 0.1181, forming a model of 27 first-level and 21 second-level indicators. The "career development expectation evaluation" held the highest weight at 26.86% in the initial assessment, while "dynamic feedback loop development" recorded the highest importance at 0.442 in the practical development phase. Practical testing demonstrated significant effectiveness, with satisfaction means ranging from M = 4.059 to 4.341. Regression analysis confirmed significant mutual influences among the model's five modules. Overall, the model effectively addresses the urgent need for personalized development strategies for private vocational college students in Yunnan Province.
Applying the Apriori Algorithm to Analyze and Optimize Medical Device Inventory Management Meidar Hadi Avizenna
Journal of Applied Data Sciences Vol 3, No 4: DECEMBER 2022
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v3i4.33

Abstract

Extracting data or an effort to retrieve valuable knowledge and information in a large database is called data mining or Knowledge Discovery in Database or usually shortened as KDD . One of the most popular algorithm in data mining technic is Apriori Algorithm, while the discovery of “relational combination pattern among itemset used Association Rules”. Data mining has been implemented into the various fields like : business or trade, education and telecommunication. In business for instance, the implementation result of data mining use ‘algorithm Apriori which can give a hand to help the Businessmen make decision on supplies. For example, the necessity of supplies system in a drugstore as one of the medical stuff supplier, and to determine which product as the priority should be supplied to anticipate out of stock of supplies availability in the store, as the results will also affect to the consumer service and daily income. Medical tools are essential unit should be supplied and being and essential factor which will impact to the consumer trust to a hospital or another medical service. That is why the availability of medical tools in drugstores is completely needed to support the success of distribution to the consumers, so the activity of medical service to consumers run thoroughly. In this case, data mining is seen as able to built intelligent business environment as solution for competing increated competition among the drugstores in future.
Predicting Gender from Online Dating Self-Introductions Using Machine Learning, Deep Learning, and DistilBERT Lionel F. Gonzalez Casanova; Wen-Ju Chen; Hsi-Sheng Wei
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.979

Abstract

This study investigates a novel approach to automated gender classification in online dating profiles by comparing models that span traditional machine learning, deep learning, and transformer-based architectures. The dataset consists of self-introduction essays from publicly accessible repositories and enriched with psychological features (LIWC), lexical features (bag-of-words), and contextual representations (raw text). The primary objective is to evaluate predictive performance, robustness, and computational cost across these modeling strategies and to assess their trade-offs. A comprehensive preprocessing pipeline was implemented, including missing-value handling, text cleaning, LIWC feature extraction, Bag-of-Words vectorization, one-hot encoding of categorical variables, and class-imbalance mitigation through random oversampling. Text augmentation using synonym replacement was subsequently applied to increase data diversity while maintaining realistic linguistic patterns. Stratified five-fold cross-validation was used for traditional models and LIWC-only deep learning experiments, and StratifiedKFold (k = 5) was applied to LIWC + BoW configurations to ensure balanced splits. DistilBERT was fine-tuned on raw essay data using an 80/20 train–test split under GPU memory and batch-size constraints. Across three runs, DistilBERT achieved an average testing accuracy of 91% ± 1%, with precision, recall, F1-score, and ROC–AUC indicating balanced performance. A GRU trained on LIWC+BoW features reached 88.62% ± 0.53% accuracy, offering competitive results at substantially lower computational cost. An MLP trained solely on LIWC features provided a stable and interpretable baseline. Confusion matrices showed balanced predictions between male and female classes, highlighting the importance of feature representation and model selection. Overall, the findings demonstrate clear trade-offs between computational demand and semantic modeling capability. These results contribute to ongoing research on gender identification and guide future work on fairness, robustness, and explainability in AI-assisted user profiling. The study also underscores practical benefits for automated analysis of unstructured text in social and psychological applications, while recognizing ethical considerations related to non-binary and gender-fluid individuals.
Current and Future Trends for Sustainable Software Development: Software Security in Agile and Hybrid Agile through Bibliometric Analysis Siti Sarah Maidin; Norzariyah Yahya; Muhammad Ashraf bin Fauri Fauzi; Normi Sham Awang Abu Bakar
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.473

Abstract

The industrial growth of digitalized era has given rise to a growing concern in software development. The present research investigates the prevailing and projected patterns in sustainable software development, especially those related to process innovation, with a particular emphasis on software security within Agile and Hybrid Agile approaches, employing bibliometric analysis. However, a comprehensive understanding of the security concerns of both agile and hybrid agile is crucial and needs further garnered. However, it is expected that a thorough comprehension of the hybrid agile model landscape would uncover various themes encompassing its implementation. The analysis aims to provide a comprehensive overview of the current, present, and future state of software security for agile and hybrid agile. The study employed a bibliometric approach to gather a total of 1593 journals from the Web of Science (WOS) database. This study utilizes co-citation and co-word analysis techniques to identify the most significant articles, delineate the fundamentals framework, and provide a prognosis for future development. The present investigation has successfully discovered four distinct co-citation and three distinct co-word clusters. This study offers valuable insights regarding the software security in agile and hybrid agile. The increasing evolution of the software ecosystem necessitates the prioritization of bridging the gap between agility and security. This paper provides a detailed roadmap for scholars and practitioners who are navigating this intersection
Edge-Deployable Multi-Class Surveillance Video Anomaly Classification Using a MobileNetV2–LSTM Spatial–Temporal Framework S Aasha Nandhini; R Karthick Manoj; Vasantakumaren S R
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1471

Abstract

Automated surveillance systems require models that can recognize abnormal events accurately while maintaining efficient inference on resource-constrained hardware. This study proposes a lightweight spatial–temporal classification framework that integrates MobileNetV2 and Long Short-Term Memory networks for identifying five surveillance activity classes: Normal, Fighting, Burglary, Road Accident, and Explosion. Surveillance videos were preprocessed through frame sampling, resizing, normalization, and fixed-length sequence construction. MobileNetV2 was employed to extract compact frame-level spatial features, while the LSTM modeled temporal dependencies across consecutive frames. The framework was evaluated using accuracy, class-wise precision, recall, F1-score, macro F1-score, weighted F1-score, confusion-matrix analysis, and probability-based anomaly scoring. Experimental results on 463 video sequences show that the proposed model achieved an accuracy of 97.41%, a macro F1-score of 0.9612, and a weighted F1-score of 0.9744. Most classification errors occurred between visually similar human-centered anomaly classes, particularly Fighting and Burglary, while Normal and Explosion sequences were recognized with very high reliability. The trained model was converted into TensorFlow Lite format and deployed on a Raspberry Pi 4, achieving approximately 6–8 frames per second with an average latency of 120–150 ms per frame. These findings indicate that the proposed MobileNetV2–LSTM framework provides an effective balance between multi-class event recognition, temporal representation learning, and near-real-time edge inference. However, further validation on larger and more diverse surveillance datasets is required to confirm its generalizability under unconstrained operational conditions.
Market Basket Analysis Using FP-Growth Algorithm to Design Marketing Strategy by Determining Consumer Purchasing Patterns Jeffri Prayitno Bangkit Saputra; Silvia Anggun Rahayu; Taqwa Hariguna
Journal of Applied Data Sciences Vol 4, No 1: JANUARY 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i1.83

Abstract

The development and competition that exists in the business world today leads every manager or company to be more dexterous in making marketing strategies to increase sales. Various things are done to keep up with existing market competition, such as analyzing customer purchase transaction data to serve as a policy determination and decision-making system in making marketing strategies. In determining marketing strategies, it can be done by taking transaction data to see existing purchase or transaction patterns. Market Basket Analysis is part of a data mining method that uses the FP-Growth algorithm technique to find out associated products. This research uses data taken from sales transaction data archives as much as 150 sales transaction data and 26 product data. In this study, it is determined that the minimum support value is 50% and the minimum confidence is ≥ 0.75 From the test results, 9 products have superior support values and meet the minimum value. From the test results, a rule with a confidence value of 0.870 was obtained: D → W (if consumers buy Wardah Lightening Gentle Wash, then buy Azarine Sunscreen SPF50), and 0.808: A → E → O (if consumers buy Emina Face Wash, then buy Azarine Night Moisturizer and Himalaya Neem Mask).