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
Bitcoin Trend Prediction Using Bitcoin Influence Index Weighted Sentiment and Hybrid Ensemble Learning Akhlis Munazilin; Mochamad Agung Wibowo; Rizky Parlika
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1322

Abstract

Predicting Bitcoin trends is a complex problem because market movements are influenced not only by historical data and technical indicators but also by sentiment and rapidly evolving information disseminated through social media. Previous studies have shown that sentiment information can improve cryptocurrency prediction; however, most approaches aggregate opinions without explicitly distinguishing the characteristics of their information sources. This study develops the Bitcoin Influence Index (BII) as a multidimensional representation of social media account influence based on four dimensions: Reach Influence, Credibility Influence, Activity Influence, and Content Influence. BII is integrated with FinBERT based sentiment analysis to construct BII weighted sentiment, which is subsequently transformed into temporal features through lag, rolling average, momentum, interaction, and shock measures. Next day Bitcoin direction is predicted using a hybrid ensemble that combines XGBoost, Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) as base learners, with Logistic Regression as the meta learner. The experiment compares two scenarios, Without BII and with BII, using 96 daily observations obtained from the integration of market and social media data. The results show that The with BII scenario increases accuracy from 40.00% to 75.00%, recall from 14.29% to 78.57%, F1-score from 0.2500 to 0.8148, and area under the curve from 0.3809 to 0.6667, while precision changes from 100.00% to 84.62%. Paired t-test yields p=0.030771, and Wilcoxon signed rank produces p=0.034808, while McNemar produces p=0.065430. These findings suggest that opinion source characteristics can provide additional predictive information when integrated with sentiment, technical indicators, and temporal models. The main contribution of this study lies in extending sentiment aware forecasting toward influence aware Bitcoin trend prediction, an approach that considers not only opinion polarity but also the multidimensional characteristics of the information sources conveying those opinions.
Modeling Gastronomy Tourists' Behavioural Intention Using eWOM, Food Authenticity, Customer Perceived Value, and Destination Image Imas Gandasari; Mohamad Rizan; Setyo Ferry Wibowo
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1519

Abstract

Understanding tourists' behavioural intention is essential for developing competitive and sustainable gastronomy tourism destinations. This study develops and validates an integrated Structural Equation Modeling (SEM) framework to examine the effects of electronic word-of-mouth (eWOM), food authenticity, customer perceived value, and destination image on gastronomy tourists' behavioural intention. A quantitative cross-sectional survey was conducted among 424 domestic gastronomy tourists in Bandung, Indonesia, and the data were analyzed using SEM. The results show that eWOM significantly influences customer perceived value and destination image but has no direct effect on behavioural intention. In contrast, food authenticity significantly enhances customer perceived value, destination image, and behavioral intention, while customer perceived value and destination image significantly mediate the effects of eWOM and food authenticity. The proposed model explains 47.5% of the variance in behavioural intention, demonstrating moderate explanatory capability. These findings extend Customer Behavior Theory, Customer Perceived Value Theory, Destination Image Formation Theory, and Food Tourism Theory by demonstrating that tourists' behavioural intention is primarily shaped through sequential cognitive evaluations rather than direct exposure to digital information. From an applied data science perspective, the study demonstrates the usefulness of SEM as a predictive modeling framework for transforming behavioural data into evidence-based decision support for sustainable gastronomy tourism management.
Impact of Digital Transformation on the Sustainability Performance of SMEs: The Moderating Role of Government Digital Support Hien Nguyen Anh; Phan Thanh Tam
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1567

Abstract

This study examines the association between digital transformation and the sustainable performance of small and medium-sized enterprises by considering the mediating roles of green innovation capability and dynamic capabilities and the moderating role of government digital support. The study integrates organizational capabilities and institutional support into a unified mechanism for explaining how digitalization is associated with economic, environmental, and social performance outcomes in an emerging economy. A two-stage design was employed: a qualitative instrument-refinement phase with structured discussions involving 35 enterprise directors in Ho Chi Minh City and Dong Nai, followed by a cross-sectional quantitative survey. This Study distributed 800 online questionnaires to respondents involved in digital transformation activities and retained 751 usable responses. The conceptual model comprised five reflective constructs and ten hypotheses. The study results show that digital transformation has the strongest direct positive association with sustainable performance and is also positively associated with green innovation capability and dynamic capabilities. Green innovation capability partially mediates the relationships between digital transformation and sustainable performance and between dynamic capabilities and sustainable performance. By contrast, dynamic capabilities do not independently mediate the digital transformation-sustainable performance relationship. Government digital support is positively associated with sustainable performance and strengthens the positive relationship between green innovation capability and sustainable performance. Given the cross-sectional, single-informant design, the findings are interpreted as associations rather than causal effects. The results suggest that managers should align digital investments with green innovation objectives, while policymakers should design digital support programs that help enterprises translate technology adoption into scalable, sustainable business outcomes.
Newton Divided Difference Optimization for Fingerprint-Based Neural Virtual Screening against Avian Influenza A/H9N2 Siti Amiroch; Mohammad Jamhuri; Awawin Mustana Rohmah; Mohammad Hamim Zajuli Al Faroby; Chairul Anwar Nidom; Reviany Vibrianita Nidom
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.v7i3.1416

Abstract

Avian influenza A/H9N2 poses persistent zoonotic and veterinary threats, yet efficient computational tools for antiviral compound prioritization remain underdeveloped, particularly with respect to optimizer behavior in high-dimensional neural screening. This study proposes Newton Divided Difference (NDD) optimization, a lightweight positive diagonal curvature-aware training strategy, as a novel optimizer for fingerprint-based neural virtual screening against avian influenza A/H9N2, with the objective of evaluating its performance across aligned molecular fingerprint representations and chemically structured validation protocols. An aligned benchmark of 1,459 molecules consisting of 615 candidate active compounds and 844 decoys was represented by EState (79 features), PubChem (881 features), and Klekota–Roth (4,860 features) fingerprints, sharing identical molecule identities, labels, and split assignments. A fixed multilayer perceptron (MLP) classifier was trained with NDD and seven baseline optimizers under stratified, scaffold-key, and similarity-cluster split protocols across five repeated seeds. NDD achieved the highest descriptive ROC-AUC (Receiver Operating Characteriztic – Area Under the Curve) and PR-AUC (Precision-Recall Area Under the Curve) on Klekota–Roth fingerprints under scaffold-key and similarity-cluster protocols, and remained competitive under the stratified split with ROC-AUC of 0.9872. Architecture-sensitivity tests confirmed stable NDD performance across multiple network configurations, with ROC-AUC values ranging from 0.9876 to 0.9890. Compared with Hessian-free optimization, NDD reduced per-run runtime from approximately 50–54 seconds to approximately 8 seconds on Klekota–Roth under the same CPU-only configuration while achieving comparable ranking performance. The novelty of this work lies in the first systematic assessment of NDD for H9N2 neural virtual screening, demonstrating that positive diagonal curvature-aware scaling provides a practical, stable, and computationally efficient optimization alternative in sparse high-dimensional ligand-based screening settings, although external validation and prospective experimental confirmation remain necessary before practical antiviral prioritization.
Digital Ecosystem Integration, Innovation Capability, and Global Market Performance of MSMEs: The Role of Institutional Support Yusmedi Nurfaizal; Arief Adhy Kurniawan; Hellik Hermawan; Dhanar Intan Surya Saputra; Muhammad Iqbal Ramadhan; Luqyana Nida Hafshah
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1527

Abstract

This study examines how Digital Ecosystem Integration, Market Intelligence Capability, Innovation Capability, and Institutional Support shape the Global Market Performance of Micro, Small, and Medium Enterprises (MSMEs) in Indonesia. Using Banyumas Regency as the empirical setting, the study proposes an integrated capability-based framework linking digital ecosystem engagement and market intelligence with global performance through Innovation Capability, while incorporating Institutional Support as a moderating condition. Data were collected through a cross-sectional survey of 100 digitally engaged MSMEs and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings show that Digital Ecosystem Integration positively affects Innovation Capability (β = 0.669; p 0.001) and Global Market Performance (β = 0.326; p 0.001). Market Intelligence Capability also positively influences Innovation Capability (β = 0.345; p 0.001) and Global Market Performance (β = 0.517; p 0.001). Innovation Capability mediates the effects of Digital Ecosystem Integration (β = 0.148; p = 0.002) and Market Intelligence Capability (β = 0.076; p = 0.014) on Global Market Performance. Institutional Support further strengthens the relationship between Innovation Capability and Global Market Performance (β = 0.184; p = 0.001). The model explains 84.3% of the variance in Global Market Performance and 68.3% in Innovation Capability, with Q² values of 0.741 and 0.584, respectively. The study extends the Dynamic Capability perspective by identifying digital ecosystem integration as a strategic capability, innovation capability as a transformation mechanism, and institutional support as a boundary condition. These findings offer practical guidance for strengthening MSME digital ecosystems and sustainable global competitiveness.
Calibrated Probabilistic Forecasting of Heavy-Tailed Financial Returns via Spiking Neural Networks with Dynamic Adaptive Computation Rani Farida Sinaga; Sutarman Sutarman; Tulus Tulus; Open Darnius
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1558

Abstract

Probabilistic forecasting of financial time series demands models that simultaneously capture heavy-tailed return distributions, time-varying volatility, and structural regime changes. Classical econometric models provide interpretable but rigid parametric specifications, while modern deep forecasting architectures achieve flexibility at the cost of substantial computational overhead. This paper introduces a novel spiking neural network augmented with dynamic adaptive computation for energy-efficient probabilistic sequence modeling. The proposed architecture processes sequential inputs through a leaky integrate-and-fire backbone with learnable, activity-dependent firing thresholds inspired by biological synaptic scaling, outputting the parameters of a Student-t distribution with input-dependent degrees of freedom. The experimental protocol employs a strict chronological train-test split to prevent data leakage. Evaluated across seven synthetic and empirical financial datasets, achieves aggregate calibration comparable to the best-performing fixed-threshold spiking baseline while substantially improving upon the classical and dense neural baselines. Specifically, it shares the lowest Mean Absolute Coverage Error of one point two zero percentage points, with statistical tests confirming significant improvements in coverage and continuous ranked probability score on heavy-tailed assets like Bitcoin. While dense baselines achieve competitive point accuracy, they exhibit severe under-coverage on these assets. In contrast, the proposed approach maintains robust calibration during extreme market regimes, as validated by formal Value-at-Risk backtests supplemented by Expected Shortfall diagnostics. Regime-stratified evaluation demonstrates that the adaptive threshold mechanism prevents the catastrophic over-coverage of classical models during high-volatility crises. Computational analysis indicates that the event-driven architecture maintains sparse spike activity, translating into an estimated ninety-eight point three percent reduction in the analytical software-level energy proxy compared to dense inference baselines. Downstream applications to volatility tracking and unsupervised anomaly detection validate the practical utility of these predictive distributions for real-time risk management, paving the way for resource-efficient models on future neuromorphic hardware.
Learning Changes Following a Structured Metacognitive Intervention among Lower-Performing Undergraduate Students in Calculus Limits Xiaoxia Liu; Sian Hoon Teoh; Geethanjali Narayanan; Walton Wider; Xiaoai Zeng
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1481

Abstract

This study examined within-student learning changes during a six-week structured metacognitive intervention among 46 lower-performing undergraduate students studying calculus limits. Participants were identified using a pragmatic, cohort-relative bottom 30% screening rule and completed content-matched 100-point achievement forms in a one-group pretest-posttest design. Mean achievement increased from 34.70 (SD = 19.56) to 59.54 (SD = 18.12), representing a mean gain of 24.85 points, t(45) = 8.27, p .001, dz = 1.22. Absolute point gains differed significantly across low-, medium-, and high-difficulty categories, F(2, 90) = 13.87, p .001, partial η² = .24. Medium-difficulty absolute gains exceeded low- and high-difficulty gains, whereas low- and high-difficulty gains did not differ significantly. Because response-format score maxima differed between forms, scores were normalized to percentages of the available maximum. Percentage-point gains differed significantly across multiple-choice, true-false, and short-answer formats after Greenhouse-Geisser correction, F(1.74, 78.18) = 8.07, p = .001, partial η² = .15. Short-answer gains exceeded those for multiple-choice and true-false formats, whereas the latter two did not differ significantly. Completion time increased significantly by 16.87 minutes, whereas the score-time ratio showed no statistically significant change. These findings characterize within-student performance changes rather than causal treatment effects, as maturation, repeated testing, concurrent instruction, instructor-related influences, and regression to the mean remain plausible alternative explanations. Planning, monitoring, evaluation, cognitive load, and implementation fidelity were not directly measured. Controlled studies incorporating direct process measures, prospective fidelity assessment, and psychometrically calibrated achievement forms are needed to test efficacy and proposed mechanisms.
Temporal Evolution of Hit Song Predictors from Spotify Audio Features: A Machine Learning and Explainable AI Study Christopher Andreas; Felicia Sword
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1506

Abstract

Understanding the factors that distinguish commercially successful songs remains an important problem in music analytics, with implications for applied data science. While previous studies have demonstrated that machine learning models can predict hit songs from audio features, they generally treat the prediction task as static and pay limited attention to how the determinants of success evolve over time. This study investigates the temporal evolution of hit-song predictors using Spotify audio features extracted from 41,103 Billboard-labelled tracks released between 1960 and 2019. The dataset is divided into three industry eras (Analog, CD/Digital, and Streaming) to examine changes in predictive performance and feature importance across distinct periods of music production and distribution. Logistic Regression, Random Forest, and K-Nearest Neighbours are optimized using grid-search cross-validation and evaluated with accuracy, F1-score, and ROC-AUC. Model interpretability is achieved through SHAP analysis. Cross-era differences in feature importance are statistically evaluated using bootstrap confidence intervals, while robustness is further assessed through repeated random seeds, permutation importance, alternative era definitions, and data de-duplication. Among the evaluated models, Random Forest consistently achieves the highest predictive performance, with ROC-AUC ranging from 0.848 to 0.917 across the three eras, indicating that chart success has become increasingly predictable from audio characteristics over time. Explainable AI analysis reveals a systematic evolution in the importance of musical attributes: instrumentalness remains the strongest predictor throughout, loudness becomes substantially more influential in the Streaming era, whereas speechiness and acousticness progressively decline in importance. These patterns are supported by bootstrap statistical testing and remain stable across multiple robustness analyses, suggesting that the observed temporal changes are not artifacts of sampling variability, model specification, or data partitioning. Overall, this study demonstrates that explainable machine learning can characterize the temporal evolution of feature importance, providing a robust analytical framework for investigating long-term changes in cultural data.
Analysis of the Determinant Factors of Decision-Making Quality in ERP Applications Muhamad Dody Firmansyah; Winson John Kerry; Eryc Eryc; Zurina Saaya; Nurul Izrin Md Saleh
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1537

Abstract

Organizations increasingly deploy cloud-based Enterprise Resource Planning (ERP) systems to achieve real-time data integration and operational efficiency, yet prior research has emphasized their transactional functions and given limited attention to how ERP quality dimensions support managerial decision-making, with most studies examining only mediated relationships. The objective of this study is to analyse the direct and indirect influence of Information Quality, System Quality, and Service Quality on Decision-Making Quality, with User Satisfaction as a mediating variable, drawing on the DeLone and McLean Information System Success Model. Its contribution and novelty lie in modelling Decision-Making Quality as a distinct outcome construct and in testing the direct paths from the three quality dimensions to decision quality alongside the mediated ones, which prior ERP research has rarely examined. Data were collected through an online five-point Likert-scale questionnaire from ERP users in Batam, Indonesia, yielding 399 valid responses analysed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS. All seven hypotheses were supported. Information Quality was the strongest determinant, affecting User Satisfaction (β = 0.535) and Decision-Making Quality (β = 0.429), followed by System Quality (β = 0.254) and Service Quality (β = 0.102); User Satisfaction significantly influenced Decision-Making Quality (β = 0.200) and acted as a partial mediator. The model explained 69.6% of the variance in Decision-Making Quality (R² = 0.696) and 54.5% in User Satisfaction (R² = 0.545). Because the design is cross-sectional and self-reported, the findings are interpreted as statistical associations rather than causal effects. Practically, the results recommend that organizations prioritise the accuracy, timeliness, and relevance of ERP information to strengthen managerial decision-making.
Toward Amodal Instance Segmentation of Overlapping Concrete Aggregates via Occlusion-Conditioned Residual Correction I Gede Teguh Satya Dharma; I Nyoman Gede Arya Astawa; I Nyoman Suardika; Made Pradnyana Ambara
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1569

Abstract

Concrete aggregate characterization is important for quality control, particularly in estimating particle size and shape distributions. Although computer vision provides a faster alternative to conventional sieve analysis, overlapping particles can hide parts of their boundaries, causing visible-only segmentation to underestimate the complete particle geometry. This study proposes an occlusion-conditioned residual correction mechanism for amodal instance segmentation of overlapping concrete aggregates. Rather than predicting the complete mask from scratch, the method preserves the observed visible region and estimates only the missing geometry along its boundary, using the visible mask as an explicit physical constraint. Local boundary information is incorporated through a ring context to guide residual prediction. The proposed mechanism is implemented within a standard Mask R-CNN framework and evaluated on a synthetic aggregate dataset with controlled occlusion levels. Compared with the corresponding direct amodal baseline, the proposed method improves AP from 48.02% to 52.69%, while ablation results show an additional gain from the ring context. Qualitative results further indicate more faithful reconstruction of irregular contours, narrow gaps, and sharp corners with less excessive mask expansion. These findings support constrained residual reconstruction as an effective mechanism for amodal aggregate segmentation under occlusion.