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
Factors Influencing Customer Repurchase Intention and Word-Of-Mouth Behavior in Food and Beverage Chain Stores Dat Tuan Nguyen; Trang Thi Kieu Ta
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.v7i3.1316

Abstract

This study investigates how customer experience attributes shape perceived value, satisfaction, repurchase intention, and word-of-mouth behavior in Vietnamese food and beverage chain stores. The study addresses the managerial problem of retaining customers in a competitive food and beverage market and contributes to the literature by clarifying a sequential value-satisfaction-behavior mechanism rather than examining isolated direct effects. Drawing on expectation conformation theory and perceived value theory, the research proposes a framework in which store atmosphere, price, perceived quality, product quality, and service quality influence perceived value; perceived value influences satisfaction; and satisfaction affects repurchase intention and word-of-mouth. A mix-methods design was used. The qualitative stage involved expert review and customer pretesting to refine measurement items and improve contextual relevance, while the quantitative stage used a structured survey of customers who had recently experienced food and beverage chain-store services in Vietnam. The research framework and seven empirical tables report the model, respondent profile, measurement items, reliability and validity indices, discriminant validity, hypothesis testing, mediation effects, and explanatory and predictive capability. After data screening, 432 valid responses were analyzed through reliability assessment, validity testing, mediation analysis, and partial least squares structural equation modeling, results show that all five  experiential factors positively influence perceived value. Store atmosphere has the strongest effect among the antecedents (β = 0.313), while price has a smaller but significant effect (β = 0.177), suggesting that customers evaluate price through the overall experience rather than cost alone. Perceived value strongly increases satisfaction (β = 0.552), and satisfaction significantly enhances both repurchase intention (β = 0.400) and word-of-mouth (β = 0.369). The findings imply that chain-store managers should coordinate atmosphere, product consistency, service responsiveness, and value-based pricing as an integrated experience system to strengthen satisfaction, repeat purchase, and customer advocacy.
Predict high school students' final grades using basic machine learning Sigit Sugiyanto
Journal of Applied Data Sciences Vol 2, No 1: JANUARY 2021
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v2i1.19

Abstract

To improve the quality of students, teachers must be able to take precautionary measures to deal with students who are lacking or have the potential to experience deficiency. Student ratings are temporary, however, have a profound impact on students' mental and enthusiasm for learning. As a teacher, it is very important to make predictions in dealing with this matter because if the ranking has been issued, it is too late. In this article, we will discuss and make Student grade predictions using basic machine learning, we will also discuss the continuity between student data and machine learning
An Improved Prediction of Transparent Conductor Formation Energy using PyCaret: An Open-Source Machine Learning Library Ayorinde Tayo Olanipekun; Daniel Mashao
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.v5i4.202

Abstract

Designing innovative materials is necessary to solve vital energy, health, environmental, social, and economic challenges. Transparent conductors are compounds that combine low absorption visible range and good electrical conductivity, which are essential properties for conductors. Technological devices such as photovoltaic cells, transistors, photovoltaic cells and sensors majorly rely on combining the two properties due to their relevancy in an optoelectronic application. Meanwhile, fewer compounds exhibit both outstanding conductivity and transparency suitable for their application in transparent conducting materials. Kaggle hosted an open big-data competition organized by novel material discovery (NOMAD) to address the importance of finding new material with the ideal functionality. The competition was organized to identify the best machine learning (ML) to predict formation enthalpy (indicating stability) for 3000  (AlxGaylnz)2NO3Ncompounds datasets; where x, y, and z can vary from the constraints x+y+z=1. Here we present a prediction using an open-source machine learning library in Python called PyCaret to summarise top-ranked ML algorithms. The gradient boosting regressor (GBR) model performed best with MAE 0.0281, MSE 0.0018 and R2 0.84. The research shows that Machine learning can significantly accelerate the discovery and optimization of materials while reducing cost of computation and required time. Low code tools like PyCaret were used to enhance the machine learning applications in materials science, paving way for more efficient materials discovery processes.
Analyzing Factors that Influence Student Performance in Academic Nieta Hidayani; Deshinta Arrova Dewi; Tri Basuki Kurniawan
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.v5i2.221

Abstract

Student performance analysis is a complex and popular study area in educational data mining. Multiple factors affect performance in nonlinear ways, making this topic more appealing to academics. The broad availability of educational datasets adds to this interest, particularly in online learning. Although previous studies have focused on analyzing and predicting students' performance based on their classroom activities, this study did not take into account student's outside conditions, such as sleep hours, extracurricular activities, and a sample of question papers that they had practiced.  These three variables are included among others in our study. In this paper, we describe an analysis of 10,000 student records, with each record containing information on numerous predictors and a performance index. The dataset intends to shed light on the relationship between predictor variables and the performance indicator. To create the correlation variable heatmap, we use both univariate and bivariate studies to produce a linear equation. Following that, we perform data preprocessing and modeling to facilitate predictive analysis. Finally, we showed the outcomes of actual and expected student performance using the model we constructed. The findings demonstrate that our prediction model was 98% accurate, with a mean absolute error of 1.62. 
Data-Driven Forecasting of Special Education Enrollment: An Explainable Machine Learning Approach Raul Alberto Garcia Castro; Wildon Rojas Paucar; Elena Miriam Chavez Garces; Rubens Houson Pérez-Mamani
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.v7i1.1046

Abstract

The application of machine learning algorithms in the field of special education remains incipient despite advances achieved in other sectors. This field faces challenges related to inclusion, planning, and resource allocation, especially in contexts where administrative records are often underutilized for analytical purposes. This study proposes an explainable forecasting approach based on 23,905 historical data records to anticipate educational demand in the Special Basic Education (SBE) modality, aiming to develop and validate a Random Forest model applied to a multivariate database of official enrollment records from 2019 to 2024, projecting a slight global contraction from 28,000 to 26,800 enrollments by 2025. The findings reveal nonlinear growth patterns differentiated by region and educational level, mainly in Early SBE (ages 0 to 2), Preschool, and Primary, with a general trend of increasing demand in coastal and highland regions. The models achieved high levels of accuracy (R² 0.97), with a Root Mean Squared Error (RMSE) below 190, a Mean Absolute Error (MAE) under 70, and a Mean Absolute Percentage Error (MAPE) below 10%. These results demonstrate the model’s utility as a strategic decision-support tool by optimizing resource planning in an education system characterized by territorial heterogeneity. The novelty of this study lies in integrating geospatial analysis and predictive algorithmic interpretability within an explainable artificial intelligence framework, fostering more equitable, transparent, and evidence-based educational planning.
Identifying Key Factors Causing Flooding Using Machine Learning Adie Wahyudi Oktavia Gama; Monalisa Dennatan; I Gusti Ngurah Putu Dharmayasa; Me Me Maw; I Putu Sugiana; Irma Suryanti
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.v6i1.463

Abstract

The impact of flooding extends beyond physical and infrastructural damage, affecting social, economic, and environmental dimensions. This study aims to identify the key factors influencing flooding by developing a decision tree model. The research method applies the C4.5 algorithm to build a decision tree model using flood factors such as rainfall, soil type, elevation, land use, and distance from rivers. The model is then applied to 57 past flood data events to determine key contributors to flooding in Denpasar City, Bali, Indonesia. The analysis showed that land elevation is the most influential factor, with areas below 28 meters above sea level having a 71% likelihood of being flood vulnerability. Additionally, the model reveals unknown patterns contributing to flood vulnerability among the factors considered. These insights give a deeper understanding of how these factors combine to affect flood vulnerability. The model's effectiveness was evaluated using a confusion matrix, resulting in an accuracy rate of 90%, a precision rate of 100%, a sensitivity rate of 90%, a specificity rate of 100%, and a F1 Score rate of 94%, demonstrating its strong predictive power in identifying areas at risk of flood vulnerability. Although this study is limited by the availability of data, the focus on Denpasar City, and the potential omission of other relevant attributes, it advances flood risk assessment by applying machine learning to provide practical insights that could enhance flood management strategies, with potential applications to other urban areas facing similar risks.
The Application of the Analytical Network Process for Select Leaders in Higher Education Institutions Phan Hong Hai; Nguyen Anh Tuan; Vo Van Tuyen
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.v7i3.1251

Abstract

This study aims to examine the application of the Analytic Network Process (ANP) in selecting leaders for public universities in Vietnam. The research seeks to develop a transparent, scientific, and decision-making framework for evaluating leadership candidates based on multiple interrelated criteria in higher education governance. Empirical data were collected from experts, lecturers, and students at a public university in Vietnam, with a total sample size of 257 respondents. The research employed pairwise comparison matrices and ANP procedures, including criteria identification, consistency testing, weight calculation, and candidate ranking. Five criteria were identified for evaluating leadership candidates: professional qualifications and scientific research capacity, ethics and integrity, experience in management and organization, ability to inspire colleagues and students, and ability to mobilize financial resources. The results indicate that ethics and integrity (C2) with weight (0.2550), ability to mobilize financial resources (C5) with weight (0.2350), and experience in management and organization (C3) with weight (0.2309) were the most influential factors in leadership selection. Based on these weighted criteria, three leadership candidates were evaluated and ranked, demonstrating the suitability and effectiveness of the ANP model in supporting decisions for selecting university leaders. The study provides a scientifically based, transparent assessment tool while suggesting policy implications in senior human resource management, in line with the requirements of innovation and sustainable development of Vietnamese higher education.
Big Data Classification of Personality Types Based on Respondents’ Big Five Personality Traits Jennifer Chi
Journal of Applied Data Sciences Vol 3, No 2: MAY 2022
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v3i2.32

Abstract

A mixed model was introduced in this study, k-means clustering analysis for data examination, discriminant analysis for classification, and multilayer perceptron neural network analysis for prediction. After deleted inadequate samples and outliers, total number of observations was 1,009,998 for this study that was collected through on interactive online personality (i.e., big five personality traits) test in 2018. Empirical results based on the k-means clustering analysis identified four different personality clusters using the total score of big five personality traits (Extraversion, Neuroticism, Agreeableness, Conscientiousness, and Openness to Experience). Results of the k-means clustering analysis were tested for accuracy using the discriminant analysis indicated that cluster means were significantly different, and showed that 95.8% of original grouped cases correctly classified. The multilayer perceptron neural network framework was utilized as a predictive model, showed a 5-5-4 neural network construction, in deciding the personality classification of participants: Training 99.5% of training grouped cases and 99.5% of testing grouped cases correctly classified. Results of this study may provide insight into the understanding of the personality of participants for further psychological, social, cultural, and economic considerations.
Designing a Culturally Adaptive Information Framework for Anxiety Disorders: A Mixed-Methods Thematic Analysis in Malaysia Achmad Udin Zailani; Wan Nooraishya Wan Ahmad; Nooralisa Muh Tuah; Nicholas Pang Tze Ping Pang Tze Ping
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.v6i3.771

Abstract

This study addresses critical gaps in Malaysia's mental health landscape by developing a culturally adaptive framework for anxiety disorder resources, where only 28% of adults recognize symptoms due to cultural stigma and poor resource design. Our key contribution is a user-centered framework integrating visual-interactive tools with cultural adaptation strategies to improve accessibility and literacy. The objective was to investigate how information design can overcome barriers, using a mixed-methods approach with 12 anxiety disorder patients (screened via DASS-21). Findings revealed: (1) format preferences (infographics: 40%, videos: 35%, simulations: 25%), (2) accessibility barriers (technical language: 45%, lack of credible sources: 65%, insufficient examples: 30%), and (3) demand for demographic personalization (age-targeted content: 78%, mood-tracking tools: 62%). Quantitative results showed strong alignment between preferred formats and comprehension gains (infographics improved understanding by 40% vs. text). The novelty lies in merging cognitive load theory with Malay cultural values (familial collectivism, Islamic coping mechanisms) into actionable design principles. Our framework demonstrates that culturally tailored visual-interactive content increases engagement by 35-40% compared to generic materials, while simplified Malay Language reduces stigma-related avoidance by 28%. These ideas translate into three evidence-based strategies: (a) minimalist visual formats to reduce cognitive load, (b) family-involved examples to respect collectivism, and (c) hybrid delivery (online/offline) for rural accessibility. The study provides policymakers with metrics-backed guidance, showing SMS-based hybrid tools achieve 58% adherence in low-bandwidth areas versus 22% for chatbots. Future work should validate scalability in larger cohorts and test AR/VR adaptations (requested by 70% of youth participants). This research advances both mental health communication theory and practical interventions for Southeast Asia's multicultural contexts.
Synchronization Patterns for Digital Twin Systems Wael Alghamdi; Emad Albassam
Journal of Applied Data Sciences Vol 5, No 3: SEPTEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i3.267

Abstract

In the area of digital twin technologies, ensuring operational accuracy and efficiency requires information alignment between the physical objects and their corresponding digital twins. This study identifies synchronization patterns that can be incorporated into the design of digital twin systems to help improve data quality, system efficiency, and alignment in digital twin systems. To identify these patterns, we conducted a comprehensive literature review and performed an analysis of synchronization techniques. With this approach, it is possible to study the advantages and limitations of various synchronization patterns, such as time-driven, event–driven, and hybrid patterns, as well as determine their applicability in different operational settings. Identified patterns are evaluated by means of simulations of several component-based software architectures. The results of the study indicate that it is crucial to identify and incorporate appropriate synchronization patterns in the design of digital systems to maximize the benefit of this technology. While some patterns work well in industrial settings, other patterns are more applicable in other domains such as health systems and smart cities. The findings offer valuable directions for future innovations and uses in various industries thereby significantly raising the field of digital twin technology.

Page 67 of 127 | Total Record : 1270