Article Per Year (5 Year)
p-Index From 2021 - 2026
2.296
P-Index
This Author published in this journals
All Journal Asia-Pacific Management and Business Application JEMA: Jurnal Ilmiah Bidang Akuntansi dan Manajemen Fair Value: Jurnal Ilmiah Akuntansi dan Keuangan J-SAKTI (Jurnal Sains Komputer dan Informatika) Data Science: Journal of Computing and Applied Informatics J-SAKTI (Jurnal Sains Komputer dan Informatika) International Journal of Advanced Science Computing and Engineering Economic and Finance in Indonesia
Patria, Harry
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Social Sciences

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Data Science: Journal of Computing and Applied Informatics

 1 
Predicting Fraudulence Transaction under Data Imbalance using Neural Network (Deep Learning) Patria, Harry
Data Science: Journal of Computing and Applied Informatics Vol. 6 No. 2 (2022): Data Science: Journal of Computing and Applied Informatics (JoCAI)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v6.i2-8309

Abstract

The number of financial transactions has the potential to cause many violations of the law (fraud). Conventional machine learning has been widely used, including logistic regression, random forest, and gradient boosted. However, the machine learning can work as long as the dataset contains fraud. Many new financial technology companies need to anticipate the potential for fraud, which they have not experienced much. This potential for a crime can also be experienced by old service providers with a low frequency of previous fraud. With the data imbalance, traditional machine learningis likely to produce false negatives so that they do not accurately predict potential fraud. This study optimizes the machine learning approach based on Neural Networks to improve model accuracy through the integration of KNIME and Python Programming with KERAS and TensorFlow models. The study also conducts a comparative analysis to scrutinize the performance of Adam and Adamax Optimizer. Using data from European cardholders in 2013, this study proves that workflows and neural network algorithms can detect with up to 95% accuracy even with a very small fraud sample of only 0.17% or 492 of 284,807 transactions. In addition, the Adam optimizer performs higher accuracy than the Adamax optimizer. The implication is that this supervisory technology innovation can be developed to minimize transaction crimes in the financial services sector.
Deciphering the Key Drivers of Sustainability : Harnessing Artificial Intelligence in Data Analytics to Unravel the Dynamics of Decarbonisation in Pursuit of Sustainable Development Patria, Harry; Djuwita A. Rahim
Data Science: Journal of Computing and Applied Informatics Vol. 8 No. 2 (2024): Data Science: Journal of Computing and Applied Informatics (JoCAI)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v8.i2-15005

Abstract

In the epoch where climate change poses an existential threat to humanity, understanding the intricate dynamics of CO2 emissions is more critical than ever. This study embarks on an ambitious journey to unravel the complex interplay of factors influencing carbon emissions, leveraging the prowess of Artificial Intelligence (AI) and the analytical capabilities of Power BI. Anchored in the context of the United Nations' Sustainable Development Goals (SDGs), this research transcends traditional analytical boundaries, offering a novel lens to view and interpret environmental data. At the heart of this exploration lies the UN SDG dataset, a rich tapestry of environmental, economic, and social indicators. The study's methodology is a fusion of advanced AI techniques with Power BI's visualization influencers, a combination that not only promises precision but also an unprecedented depth of insight. This dual approach enables a multifaceted analysis, capturing the nuances and subtleties often lost in conventional studies. The findings of this research are both revealing and transformative. They shed light on the significant yet varied factors that drive CO2 emissions across different geographical and socio-economic landscapes. The study unveils a striking correlation between increased access to electricity and GDP per capita with rising carbon emissions, a pattern particularly pronounced in developing regions. Conversely, in more developed contexts, the analysis reveals a complex interplay between emissions, literacy rates, and fertility rates, suggesting indirect yet potent pathways through which socio-economic development influences environmental outcomes. The insights gleaned offer a beacon for policymakers, illuminating the pathways to tailor environmental strategies that resonate with the unique needs of different regions. For developing nations, the study advocates for policies that intertwine educational and family planning initiatives with environmental objectives. In contrast, for developed countries, it underscores the need for technological innovation and efficiency improvements. The study's innovative use of AI and Power BI sets a new precedent in environmental research, demonstrating the immense potential of these tools in shaping sustainable futures.
Bayesian Regression for Predicting Price Empirical Evidence in American Real Estate Patria, Harry
Data Science: Journal of Computing and Applied Informatics Vol. 7 No. 1 (2023): Data Science: Journal of Computing and Applied Informatics (JoCAI)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v7.i1-10082

Abstract

The two foremost aims of classical regression are to assess the structure and magnitude of the relationship between variables. Despite the aforementioned benefits, unlike classical regression, which only offers a point estimate and a confidence interval, Bayesian regression offers the whole spectrum of inferential solutions. The results of this study demonstrate the Bayesian approach's suitability for regression tasks and its advantage in accounting for additional a priori data, which often strengthens studies. Using data from Boston Housing provided by from UCI ML Repository, this study proves that the prior distributions have the benefit of producing analytical, closed-form conclusions, which eliminates the need to use numerical techniques like Markov Chain Monte Carlo (MCMC). Second, software implementations are offered together with formulas for the posterior outcomes that are supplied, clarified, and shown. The assumptions supporting the suggested approach are evaluated in the third step using Bayesian tools. Prior elicitation, posterior calculation, and robustness to prior uncertainty and model sufficiency are the three processes that are essential to Bayesian inference.
Price Prediction with Bayesian Inference and Visualization: Empirical Evidence in India Real Estate Patria, Harry
Data Science: Journal of Computing and Applied Informatics Vol. 7 No. 2 (2023): Data Science: Journal of Computing and Applied Informatics (JoCAI)
Publisher : Talenta Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jocai.v7.i2-11434

Abstract

Classical regression serves two primary purposes: evaluating the structure and strength of the relationship between variables. However, while classical regression provides only a point estimate and confidence interval, Bayesian regression offers a comprehensive range of inferential solutions. This study demonstrates the suitability of the Bayesian approach for regression tasks and its advantage in incorporating additional a priori information, which can strengthen research. To illustrate, we utilized data from the Indian Housing dataset provided by the Kaggle Repository. We found that prior distributions produce analytical, closed-form conclusions, eliminating the need for numerical techniques like Markov Chain Monte Carlo (MCMC). Furthermore, this study provides software implementations, along with formulas for the posterior outcomes that are explained and presented clearly. In the third step, Bayesian tools were employed to evaluate the assumptions that underlie the proposed approach. Specifically, the essential processes of Bayesian inference - prior elicitation, posterior calculation, and robustness to prior uncertainty and model sufficiency - were assessed.
Co-Authors Aromy, Verry Dina B, Yanuardhi Arief Daulay, Iman Taufiq Dina Anggraeni, Dina Djuwita A. Rahim Fadillah, Lukman Farih, Imaduddin Heri Hermawan Margono, Hanif Nur Fauzi Nadira, N Nugraha, Raditya Hari Nugroho, Antonius Agung Prasetyo, Heru Budi Prasetyohadi, Latif Rahim, Djuwita A. Satya, Candra Harry Sugiyanto, Kris Syarif, Allevia Tryanda, Dendy Yuwono, Eko Zam Zam, M. Irwan Zulfikri, Fahmi