cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Andhika Rafi Hananto
Contact Email
andhikarh90@gmail.com
Phone
+6282314736799
Journal Mail Official
support@jdmdc.com
Editorial Address
Graha Permata Estate, Jl. HM Bahrun Blok H9, Sokayasa, Berkoh, Kec. Purwokerto Tim., Kabupaten Banyumas, Jawa Tengah 53146
Location
Kab. banyumas,
Jawa tengah
INDONESIA
Journal of Digital Market and Digital Currency
Published by Meta Bright Indonesia
ISSN : -     EISSN : 30480981     DOI : https://doi.org/10.47738/jdmdc
Core Subject : Economy, Science,
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance
Journal of Digital Market and Digital Currency publishes high-quality research on: Digital Marketing Digital Currencies Cryptocurrency Trends Blockchain Applications Fintech Innovations Our goal is to provide a platform for researchers, practitioners, and policymakers to share innovative findings, discuss emerging trends, and address the challenges and opportunities presented by the Journal of Digital Market and Digital Currency.
Arjuna Subject : Bisnis, Menejemen, dan Akutansi (semua kategori) - Bisnis, Menejemen, dan Akutansi (Lain-Lain)
Articles 40 Documents
 1   2   3   4 
Enhancing Short-Term Price Prediction of TON-IRT Using LSTM Neural Networks: A Machine Learning Approach in Blockchain Trading Analytics Stephanus, Alphin; Mbitu, Elisabeth Tansiana
Journal of Digital Market and Digital Currency Vol. 2 No. 4 (2025): Regular Issue December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v2i4.43

Abstract

This study explores the application of Long Short-Term Memory (LSTM) neural networks for predicting short-term price movements of the TON-IRT trading pair in the cryptocurrency market. Given the high volatility and complexity of cryptocurrency prices, traditional models like Linear Regression and ARIMA often fail to capture the underlying non-linear and temporal dependencies. To address this, we implemented an LSTM model, a type of recurrent neural network specifically designed for sequential data. The model was trained on historical hourly data, utilizing various technical indicators and lagged features to improve prediction accuracy. Our results demonstrated that the LSTM model significantly outperformed traditional methods, achieving a Mean Absolute Error (MAE) of 0.0274, a Root Mean Squared Error (RMSE) of 0.0321, and an R-squared (R²) value of 0.8743, which indicated that the model captured over 87% of the variance in the actual price data. Visual analysis of predicted versus actual prices revealed a strong alignment, though some lag in predictions during high-volatility periods was observed. The model also showed a tendency to underestimate price peaks, highlighting areas for further refinement. This study contributes to the field of blockchain trading analytics by demonstrating the effectiveness of LSTM models in addressing the unique challenges of cryptocurrency price prediction. Practical implications for traders and investors include the ability to enhance trading strategies, optimize entry and exit points, and improve risk management. Future research could integrate additional external factors, such as market sentiment and news events, or explore advanced architectures like Transformer models. By doing so, the predictive capabilities of LSTM models in volatile markets like cryptocurrency could be further refined, leading to more robust and accurate forecasting tools for financial decision-making.
Sentiment Analysis of Mobile Legends Play Store Reviews Using Support Vector Machine and Naive Bayes Alkhoze, Mona; Almasre, Miada
Journal of Digital Market and Digital Currency Vol. 2 No. 4 (2025): Regular Issue December 2025
Publisher : Bright Publisher

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

Abstract

This study applies sentiment analysis to Mobile Legends Play Store reviews to classify user feedback as positive, negative, or neutral, offering insights into the factors influencing user satisfaction. Utilizing machine learning models—Naive Bayes and Support Vector Machine (SVM)—user sentiment is evaluated, and key themes in user feedback are identified. Both models demonstrate high accuracy, with SVM slightly outperforming Naive Bayes. Specifically, the SVM model records an accuracy of 84.95%, a precision of 81.76%, and an F1-score of 83.31%, while Naive Bayes achieves an accuracy of 84.10%, a precision of 82.09%, and an F1-score of 82.57%. This classification highlights a predominance of positive reviews, revealing players’ appreciation for the game's graphics and gameplay. In contrast, negative reviews expose common frustrations related to lag and technical issues, indicating areas for potential improvement. The analysis also uncovers the challenge of accurately classifying neutral sentiments due to the informal language and slang found in reviews written in Bahasa Indonesia. Future studies could address this by incorporating advanced NLP techniques, such as word embeddings or deep learning models, to better capture linguistic nuances. Overall, this research provides actionable insights for game developers, enabling them to prioritize updates and feature enhancements that align with player preferences and feedback trends.
Understanding User Satisfaction in Digital Finance Through Sentiment Analysis of User Reviews Angelia, Chininta Rizka; Nurhayati, Kristina; Amalia, Dinda
Journal of Digital Market and Digital Currency Vol. 2 No. 4 (2025): Regular Issue December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v2i4.45

Abstract

This study conducted a sentiment analysis on 100,000 user reviews of the Kredivo app to assess user satisfaction and identify areas for improvement in the context of digital finance. Leveraging Term Frequency-Inverse Document Frequency (TF-IDF) for feature extraction and employing Logistic Regression and Support Vector Machine (SVM) models, the analysis revealed a predominantly positive user sentiment, with 62% of the reviews classified as positive, 25% as negative, and 13% as neutral. Positive reviews frequently highlighted the app's ease of use and quick access to credit, indicating high satisfaction with its functionality and convenience. In contrast, negative reviews commonly cited issues with customer service responsiveness and transparency around fees, suggesting areas where the app could enhance user experience. Visualizations, including a confusion matrix and sentiment distribution charts, further illustrated the model's accuracy and user sentiment patterns. The study’s findings align with previous research in digital finance, which emphasizes the critical role of user feedback in app development and user retention. However, unique insights regarding the challenges faced by buy-now-pay-later (BNPL) platforms like Kredivo were also observed, notably around customer service and fee transparency. The study highlights the potential of sentiment analysis as a tool for digital finance app developers to continuously improve service quality. Limitations include potential biases in the dataset and model limitations, suggesting future research directions that incorporate additional data sources and advanced NLP models.
Sentiment Analysis of User Reviews on Cryptocurrency Trading Platforms Using Pre-Trained Language Models for Evaluating User Satisfaction Javadi, Milad; Sugianto, Dwi; Sarmini
Journal of Digital Market and Digital Currency Vol. 2 No. 4 (2025): Regular Issue December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v2i4.46

Abstract

The study examines user sentiment on the Indodax cryptocurrency trading platform using pre-trained Indonesian language models for sentiment analysis. A dataset of 25,000 user reviews was analyzed, revealing that most reviews expressed neutral sentiment, with positive sentiments accounting for 20% and negative sentiments under 4%. The sentiment classification models used include Support Vector Machine (SVM), Logistic Regression, and Naive Bayes. SVM achieved the highest predictive accuracy at 94.22%, followed by Logistic Regression at 93.62%. These models classified sentiments based on TF-IDF feature extraction, highlighting SVM's effectiveness in sentiment classification within the user reviews. Additionally, sentiment trends over time were analyzed, showing fluctuations in user satisfaction corresponding with market events and platform changes, emphasizing the importance of maintaining platform stability during high volatility. The study’s findings suggest actionable improvements for Indodax, such as addressing user concerns that lead to negative sentiments, like customer service and technical issues, while reinforcing platform strengths, such as ease of use. These insights enable Indodax to enhance user satisfaction and retention by monitoring sentiment trends and adjusting features accordingly. However, the study faces limitations due to the use of pre-trained models that may not fully capture Indonesian language nuances and the absence of demographic data, which limits the analysis to general sentiment trends. Future research could incorporate demographic insights and user behavior metrics to offer a more personalized understanding of user sentiment, ultimately aiding Indodax in delivering a more tailored and satisfying user experience.
Uncovering Key Service Improvement Areas in Digital Finance: A Topic Modeling Approach Using LDA on User Reviews Othman, Jalel Ben; Hariguna, Taqwa
Journal of Digital Market and Digital Currency Vol. 2 No. 4 (2025): Regular Issue December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v2i4.47

Abstract

The rapid expansion of digital finance has transformed the way financial services are accessed and utilized, particularly in emerging markets such as Indonesia. This study aims to uncover key service improvement areas within the Easycash mobile lending platform by analyzing user reviews through topic modeling using Latent Dirichlet Allocation (LDA). The research employed a data-driven approach, combining text preprocessing in Bahasa Indonesia using the Sastrawi library, TF-IDF vectorization, and sentiment classification with machine learning models including Naive Bayes, K-Nearest Neighbors (KNN), and XGBoost. The XGBoost model achieved the highest performance with an F1-score of 0.9709, effectively distinguishing between positive, neutral, and negative sentiments. LDA analysis identified five major topics: Loan Limits and Repayment, Customer Gratitude and Satisfaction, Loan Application Process and Interest Rates, App Quality and Customer Service, and Data Management and Account Issues. Results indicate that while Easycash users generally express positive sentiment toward ease of use and service speed, concerns persist regarding high interest rates, customer service responsiveness, and data privacy. These findings provide actionable insights for fintech companies to enhance user satisfaction through targeted service improvements and continuous feedback analysis.
Assessing the Impact of Credit Score and Employment Stability on Loan Approval Using Logistic Regression Mohammed, El Felhi; Mirlam, Maram Saleh
Journal of Digital Market and Digital Currency Vol. 3 No. 1 (2026): Regular Issue March 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v3i1.53

Abstract

This study investigates the determinants of loan approval decisions using a Logistic Regression approach based on applicants’ financial and employment characteristics. The dataset consists of key predictors, including income, credit score, loan amount, years employed, and points, which were analyzed to assess their influence on loan approval outcomes. Data preprocessing was conducted through z-score normalization, and the dataset was divided into training (80%) and testing (20%) subsets. The Logistic Regression model demonstrated exceptional predictive performance, achieving perfect values across all evaluation metrics, including Accuracy (1.000), Precision (1.000), Recall (1.000), F1-score (1.000), and ROC-AUC (1.000). These results indicate that the model was able to perfectly distinguish between approved and rejected loan applications. Further examination of model coefficients and odds ratios revealed that credit score and points were the most significant predictors positively influencing loan approval probability, while loan amount exhibited a negative relationship. The findings emphasize that creditworthiness and institutional scoring systems play a dominant role in financial decision-making, whereas income and employment history have a moderate but supportive influence. Although the model’s perfect performance highlights strong predictive capability, it may also reflect a highly structured or synthetic dataset, suggesting the need for validation using larger and more diverse samples. The study contributes to the growing literature on data-driven financial analytics by demonstrating that Logistic Regression remains a powerful and interpretable tool for assessing credit risk and improving loan approval transparency.
Causal Relationship Between AI R&D Investment and Stock Market Performance Using VAR and Granger Causality Models Salem, Abdel Badeeh M.; Aqel, Musbah J.
Journal of Digital Market and Digital Currency Vol. 3 No. 1 (2026): Regular Issue March 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v3i1.54

Abstract

This study investigates the causal relationship between Artificial Intelligence (AI) R&D investment and stock market performance using a time-series econometric framework. Drawing on data from AI-driven firms between 2015 and 2024, the research applies Vector Autoregression (VAR) and Granger Causality models to explore whether innovation spending influences short-term financial outcomes. The analysis employs monthly aggregated data on AI R&D Spending and Stock Market Impact, supported by correlation analysis, impulse response estimation, and forecast error variance decomposition. The results indicate that AI R&D investment and market performance exhibit no statistically significant short-term causal linkage, as confirmed by non-significant Granger p-values (p > 0.05) and weak correlation (r = 0.13). The Impulse Response Function (IRF) shows a transient positive effect of R&D shocks on stock performance, peaking at approximately +0.12% before dissipating after the fourth period. Meanwhile, the Forecast Error Variance Decomposition (FEVD) reveals that more than 99% of the variance in R&D spending is explained by its own historical dynamics, suggesting minimal feedback from market reactions. These findings collectively imply that AI R&D investments operate on a long-term strategic horizon, while financial markets react within short-term informational cycles, creating a temporal disconnect between innovation effort and market recognition. The study contributes to the literature on innovation-finance dynamics by providing empirical evidence that technological progress and financial valuation evolve asynchronously, reflecting their inherently different timeframes and behavioral logics.
Deep Learning-Based Loan Approval Prediction Using Artificial Neural Network (ANN) and Feature Importance Analysis Armoogum, Sheeba; Dewi, Deshinta Arrova; Armoogum, Vinaye; Melanie, Nicolas; Kurniawan, Tri Basuki
Journal of Digital Market and Digital Currency Vol. 3 No. 1 (2026): Regular Issue March 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v3i1.55

Abstract

The increasing demand for efficient and objective credit evaluation has motivated the adoption of artificial intelligence in financial decision-making. This study proposes a deep learning-based loan approval prediction model using an Artificial Neural Network (ANN) combined with feature importance analysis to enhance interpretability. The dataset, consisting of 2,000 loan application records with both financial and demographic attributes, was preprocessed through normalization and one-hot encoding to ensure consistent feature representation. The ANN model was trained using three hidden layers (64–32–16 neurons) with the ReLU activation function and optimized using Adam with early stopping to prevent overfitting. Experimental results demonstrate that the proposed ANN model achieves an accuracy of 92%, with a precision of 0.91, a recall of 0.93, and a ROC-AUC of 0.95, indicating excellent classification capability. The Permutation Feature Importance analysis revealed that Credit Score, Income, and Loan Amount are the most significant predictors influencing loan approval decisions. These findings confirm that the ANN model can capture complex non-linear relationships among financial attributes while maintaining transparency through explainable AI techniques. The proposed approach contributes both theoretically and practically by combining predictive power with interpretability, offering a reliable and explainable framework for automating loan evaluation in modern financial institutions.
The Impact of Financial News Sentiment on Market Index Volatility through Event-Driven Analysis Using Random Forest and Linear Regression Models Latina, Ellen Joy; Abdurahman, Mar Jane
Journal of Digital Market and Digital Currency Vol. 3 No. 1 (2026): Regular Issue March 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v3i1.56

Abstract

This study investigates the impact of financial news sentiment on market index volatility using an event-driven analytical approach combined with machine learning models. Two predictive algorithms, Linear Regression and Random Forest Regressor, were employed to evaluate how sentiment polarity, market event type, trading volume, and sector classification influence short-term index fluctuations. The results demonstrate that both models have limited explanatory power, as reflected by low and negative R² values (−0.0147 and −0.1479), indicating that sentiment polarity alone cannot adequately capture market volatility. Feature importance analysis revealed that Trading Volume (0.48) and Market Event Type (0.31) are the most influential predictors, while Sentiment Score (0.14) contributes marginally. These findings suggest that market volatility is primarily volume-driven and event-reactive, with sentiment serving as a secondary amplifier rather than a direct causal factor. The study concludes that combining sentiment analysis with quantitative and temporal indicators may improve the modeling of complex market dynamics in future research.
Market Regime Detection in Bitcoin Time Series Using K-Means Clustering and Hidden Markov Models Haryani, Calandra A.; Chandra; Tarigan, Riswan Efendi
Journal of Digital Market and Digital Currency Vol. 3 No. 1 (2026): Regular Issue March 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jdmdc.v3i1.57

Abstract

The rapid growth of cryptocurrency markets has created new challenges in understanding and predicting the structural dynamics of digital asset prices. Bitcoin, as the most traded blockchain-based currency, exhibits extreme volatility, nonlinear patterns, and complex regime shifts that traditional financial models cannot adequately capture. This study proposes a hybrid analytical framework that integrates K Means clustering with the Hidden Markov Model to identify and model multiple market regimes in Bitcoin time series data. The Bitcoin dataset used in this research contains minute-level records that were preprocessed to extract key indicators, namely logarithmic returns and rolling volatility, which represent the short-term dynamics of market behavior. The K Means algorithm was first employed to segment the data into three distinct clusters that correspond to bullish, bearish, and sideways regimes, followed by the application of the Hidden Markov Model to estimate probabilistic transitions between these regimes over time. The results reveal that the hybrid K Means and Hidden Markov Model approach achieves superior performance compared to a standalone model, as indicated by a higher log likelihood and a lower Bayesian Information Criterion value. The transition probability matrix shows that bullish and bearish regimes are highly persistent, while the sideways regime acts as a transitional buffer that connects both market extremes. The empirical findings confirm that Bitcoin prices evolve through persistent and probabilistically determined regimes rather than random fluctuations. The proposed framework provides a more comprehensive understanding of cryptocurrency market dynamics and offers practical value for investors, risk analysts, and policymakers in designing adaptive trading and risk management strategies within blockchain-based financial ecosystems.

Page 4 of 4 | Total Record : 40

 1   2   3   4 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 1 (2026): Regular Issue March 2026 Vol. 2 No. 4 (2025): Regular Issue December 2025 Vol. 2 No. 3 (2025): Regular Issue September 2025 Vol. 2 No. 2 (2025): Regular Issue June 2025 Vol. 2 No. 1 (2025): Regular Issue March Vol. 1 No. 1 (2024): Regular Issue June 2024 Vol. 1 No. 3 (2024): Regular Issue December Vol. 1 No. 2 (2024): Regular Issue September