Article Per Year (5 Year)
p-Index From 2021 - 2026
4.41
P-Index
This Author published in this journals
All Journal International Journal of Business, Economics, and Social Development Narra X Journal of Computing Theories and Applications Leuser Journal of Environmental Studies Ekonomikalia Journal of Economics Journal of Educational Management and Learning Infolitika Journal of Data Science Indatu Journal of Management and Accounting The International Journal of Financial Systems Grimsa Journal of Business and Economics Studies Journal of Future Artificial Intelligence and Technologies
Irsan Hardi
Economic Modeling And Data Analytics Unit, Graha Primera Saintifika, Aceh Besar 23371, Indonesia
Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Energy Engineering Environmental Science Immunology & microbiology Languange, Linguistic, Communication & Media Materials Science & Nanotechnology Mathematics Medicine & Pharmacology Physics Public Health Social Sciences Other

Published : 33 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 33 Documents
Search

 1   2   3   4 
An Interpretable Machine Learning Strategy for Antimalarial Drug Discovery with LightGBM and SHAP Noviandy, Teuku Rizky; Idroes, Ghalieb Mutig; Hardi, Irsan
Journal of Future Artificial Intelligence and Technologies Vol. 1 No. 2 (2024): September 2024
Publisher : Future Techno Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/faith.2024-16

Abstract

Malaria continues to pose a significant global health threat, and the emergence of drug-resistant malaria exacerbates the challenge, underscoring the urgent need for new antimalarial drugs. While several machine learning algorithms have been applied to quantitative structure-activity relationship (QSAR) modeling for antimalarial compounds, there remains a need for more interpretable models that can provide insights into the underlying mechanisms of drug action, facilitating the rational design of new compounds. This study develops a QSAR model using Light Gradient Boosting Machine (LightGBM). The model is integrated with SHapley Additive exPlanations (SHAP) to enhance interpretability. The LightGBM model demonstrated superior performance in predicting antimalarial activity, with an ac-curacy of 86%, precision of 85%, sensitivity of 81%, specificity of 89%, and an F1-score of 83%. SHAP analysis identified key molecular descriptors such as maxdO and GATS2m as significant contributors to antimalarial activity. The integration of LightGBM with SHAP not only enhances the predictive ac-curacy of the QSAR model but also provides valuable insights into the importance of features, aiding in the rational design of new antimalarial drugs. This approach bridges the gap between model accuracy and interpretability, offering a robust framework for efficient and effective drug discovery against drug-resistant malaria strains.
Energy Poverty and Environmental Quality Nexus: Empirical Evidence from Selected South Asian Countries Sikdar, Asaduzzaman; Bani, Nor Yasmin binti Mhd; Salimullah, Abul Hasnat Muhammed; Majumder, Shapan Chandra; Idroes, Ghalieb Mutig; Hardi, Irsan
Ekonomikalia Journal of Economics Vol. 2 No. 2 (2024): October 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/eje.v2i2.221

Abstract

South Asian countries are included in the economies of developing Asia. The region of South Asia is predominantly affected by energy poverty issues due to a heavy reliance on conventional energy and unpredictable access to energy services. It has about a quarter of the world's population and is home to three of the world's ten most populated countries: India, Pakistan, and Bangladesh. This study investigates environmental sustainability dynamics in South Asian countries from 2000 to 2021, utilizing the Cross-sectional Autoregressive Distributed Lag (CS-ARDL) and Dumitrescu-Hurlin (D-H) causality methods. The research offers insights into the long-term trends and causal relationships that shape environmental outcomes in South Asian nations. Based on empirical findings, in the long-term, it is revealed that increases in energy poverty, economic growth, income inequality, and capital formation raise greenhouse gas (GHG) emissions, while renewable energy and labor reduce GHG emissions. On the other hand, the error correction term shows the speed of adjustment toward equilibrium at 0.75%. Furthermore, the D-H panel causality reveals a directional link between variables. These findings highlight the urgent need for South Asian countries to implement policies to address energy poverty, promote renewable energy adoption, and reduce income inequality to mitigate GHG emissions and achieve long-term environmental sustainability effectively.
Prognostication of differentiated thyroid cancer recurrence: An explainable machine learning approach Idroes, Ghazi M.; Noviandy, Teuku R.; Idroes , Ghalieb M.; Hardi, Irsan; Duta, Teuku F.; Hamoud, Lama MA.; Al-Gunaid , Hala T.
Narra X Vol. 2 No. 3 (2024): December 2024
Publisher : Narra Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52225/narrax.v2i3.183

Abstract

Differentiated thyroid cancer (DTC) generally has a favorable prognosis, but recurrence remains a concern for a subset of patients, highlighting the need for accurate predictive tools. While traditional methods, such as the American Thyroid Association (ATA) guidelines, are widely used, they may not fully capture the complex patterns in clinical data. To address this, we developed a machine learning model using LightGBM and enhanced its interpretability with SHAP (SHapley Additive exPlanations). Our model, trained on data from 383 DTC patients, identified response to initial therapy as the most significant predictor of recurrence, alongside age and risk level. The model achieved an accuracy of 93.51%, with precision and sensitivity of 94.23% and 96.08%, respectively, using only five key features selected through Recursive Feature Elimination (RFE). SHAP analysis provided clear insights into how these features influenced predictions, offering a transparent and interpretable approach to risk stratification. These results highlight the potential of explainable machine learning to improve recurrence prediction, support personalized care, and build clinician trust, while laying the groundwork for further validation in diverse populations.
Forecasting Bank Stock Trends Using Artificial Intelligence: A Deep Dive into the Neural Prophet Approach Noviandy, Teuku Rizky; Hardi, Irsan; Idroes, Ghalieb Mutig
The International Journal of Financial Systems Vol. 2 No. 1 (2024)
Publisher : Otoritas Jasa Keuangan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61459/ijfs.v2i1.41

Abstract

This research aims to use Neural Prophet, a deep learning tool, to predict stock prices in the banking sector with high accuracy and useful insights. The model's capability in managing intricate temporal patterns differentiates it, garnering attention from researchers. The significance of this research lies in its potential to enhance stock price prediction precision, especially in the context of banking stocks, offering stakeholders’ deeper insights. The model's efficacy spans stable and volatile market behaviours, making it a valuable tool for informed decision-making in finance. Accurate predictions benefit risk management, facilitating well-informed investment choices in dynamic markets.
Long-Term Impact of Dirty and Clean Energy on Indonesia’s Economic Growth: Before and During the COVID-19 Pandemic Ringga, Edi Saputra; Hafizah, Iffah; Idroes, Ghifari Maulana; Amalina, Faizah; Kadri, Mirzatul; Idroes, Ghalieb Mutig; Noviandy, Teuku Rizky; Hardi, Irsan
Grimsa Journal of Business and Economics Studies Vol. 2 No. 1 (2025): January 2025
Publisher : Graha Primera Saintifika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61975/gjbes.v2i1.49

Abstract

Dirty (non-renewable) energy, considered environmentally harmful due to greenhouse gas emissions, is contrasted with clean (renewable) energy, which is believed to have positive ecological impacts that can boost economic growth in the long term. This study analyzes the long-term effects of electricity generation from both dirty and clean energy sources on economic growth in Indonesia, using data from two periods: before the COVID-19 pandemic (2000–2019) and the full period including the COVID-19 pandemic (2000–2022). Empirical findings from Fully Modified Ordinary Least Squares (FMOLS) and Dynamic Ordinary Least Squares (DOLS) methods reveal that dirty energy significantly impacts long-term economic growth in both periods, while clean energy does not have a substantial effect. A robustness check conducted using the Canonical Cointegrating Regression (CCR) method confirms that dirty energy continues to play a crucial role in Indonesia's long-term economic growth. A key finding is that the positive impact of dirty energy generation on economic growth was stronger in the full period including the COVID-19 pandemic compared to before. This suggests that dirty energy contributed more to economic growth during the pandemic. The study recommends a balanced approach to economic growth by prioritizing the transition to clean energy while recognizing the importance of dirty energy in Indonesia's economy. This transition should be gradual, using the current role of dirty energy to support economic development while investing in clean energy alternatives for sustainable growth.
Prognostication of differentiated thyroid cancer recurrence: An explainable machine learning approach Idroes, Ghazi M.; Noviandy, Teuku R.; Idroes , Ghalieb M.; Hardi, Irsan; Duta, Teuku F.; Hamoud, Lama MA.; Al-Gunaid , Hala T.
Narra X Vol. 2 No. 3 (2024): December 2024
Publisher : Narra Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52225/narrax.v2i3.183

Abstract

Differentiated thyroid cancer (DTC) generally has a favorable prognosis, but recurrence remains a concern for a subset of patients, highlighting the need for accurate predictive tools. While traditional methods, such as the American Thyroid Association (ATA) guidelines, are widely used, they may not fully capture the complex patterns in clinical data. To address this, we developed a machine learning model using LightGBM and enhanced its interpretability with SHAP (SHapley Additive exPlanations). Our model, trained on data from 383 DTC patients, identified response to initial therapy as the most significant predictor of recurrence, alongside age and risk level. The model achieved an accuracy of 93.51%, with precision and sensitivity of 94.23% and 96.08%, respectively, using only five key features selected through Recursive Feature Elimination (RFE). SHAP analysis provided clear insights into how these features influenced predictions, offering a transparent and interpretable approach to risk stratification. These results highlight the potential of explainable machine learning to improve recurrence prediction, support personalized care, and build clinician trust, while laying the groundwork for further validation in diverse populations.
Innovation and Carbon Emissions: A Southeast Asian Perspective Hardi, Irsan; Çoban, Mustafa Necati; Fumey, Michael Provide
Ekonomikalia Journal of Economics Vol. 3 No. 1 (2025): April 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/eje.v3i1.275

Abstract

In an era where sustainable development is paramount, understanding the relationship between innovation and environmental impact has become increasingly critical. As Southeast Asian (SEA) economies strive to transition toward more knowledge-based and technology-driven growth, it is crucial to assess whether innovation fosters sustainability or exacerbates environmental degradation. This study examines the impact of the innovation ecosystem on CO2 emissions in selected SEA countries, utilizing various metrics from the Global Innovation Index (GII) grouped into five categories: institutions, human capital and research, infrastructure, market sophistication, and creative outputs. By employing Generalized Linear Models (GLMs) and conducting robustness checks with Robust Least Squares (RLS), the study reveals that all GII categories significantly impact CO2 emissions. However, the findings indicate that this impact is positive, meaning that the innovation landscape in SEA continues to contribute to rising CO2 emissions. The country-specific analysis also confirms that most of the GII categories are still not environmentally friendly. This evidence underscores the need for policymakers in SEA countries to prioritize the development of environmentally sustainable innovation frameworks that promote the adoption of inclusive green technologies and practices to mitigate the adverse effects of innovation on CO2 emissions.
An Explainable Machine Learning Study of Behavioral and Psychological Determinants of Depression in the Academic Environment Noviandy, Teuku Rizky; Idroes, Ghalieb Mutig; Hardi, Irsan; Ringga, Edi Saputra; Idroes, Rinaldi
Journal of Educational Management and Learning Vol. 3 No. 1 (2025): May 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/jeml.v3i1.304

Abstract

Depression is a significant and growing concern within academic environments, affecting both students and staff due to factors such as academic pressure, financial stress, and lifestyle challenges. This study explores the use of machine learning, specifically a Random Forest classifier, to predict depression risk among students using behavioral, psychological, and demographic data. A dataset of 27,788 student records was analyzed after thorough preprocessing and exploratory data analysis. The model achieved strong performance, with an accuracy of 83.52% and an AUC of 0.91, indicating reliable classification of depression status. Local Interpretable Model-agnostic Explanations (LIME) were employed to enhance interpretability, revealing key predictive features such as suicidal ideation, academic pressure, sleep duration, and dietary habits. These interpretable insights align with existing psychological research and provide actionable information for mental health professionals. The findings highlight the value of explainable AI in educational settings, offering a scalable and transparent approach to early depression detection and intervention. Future work should focus on longitudinal data integration, multimodal inputs, and real-world implementation to strengthen the model’s utility and impact.
Do Business Conditions Drive FDI Inflows? A Decomposition Analysis Using B-READY Indicators Hardi, Irsan; Çoban, Mustafa Necati; Maulana, Ar Razy Ridha; Idroes, Ghalieb Mutig; Mardayanti, Ulfa
Indatu Journal of Management and Accounting Vol. 3 No. 1 (2025): June 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijma.v3i1.303

Abstract

Foreign direct investment (FDI) is essential for economic development and business sustainability, and understanding the business conditions that attract it remains a key policy concern. This study adopts a decomposition approach by examining the impact of various B-READY indicators on FDI inflows in separate models, using cross-sectional data from 45 countries. To ensure methodological rigor, it applies three Robust Least Squares (RLS) estimation techniques: M-type, S-type, and MM-type. The findings reveal that six out of ten B-READY indicators exert a positive and statistically significant influence on FDI inflows. The significant B-READY indicators, such as business insolvency, dispute resolution, international trade, labor, market competition, and taxation, highlight critical factors that businesses consider when entering or expanding in foreign markets. These insights offer valuable guidance and practical implications not only for policymakers seeking to strengthen national investment environments, but also for businesses evaluating market readiness and investment risks in foreign economies.
Firm-Level and Public-Sector Corruption Perceptions: The Nexus Hardi, Irsan; Adam, Muhammad; Ringga, Edi Saputra
Indatu Journal of Management and Accounting Vol. 3 No. 1 (2025): June 2025
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijma.v3i1.310

Abstract

Understanding how firm-level corruption shapes national corruption perceptions is crucial for both policymakers and businesses, as it provides evidence to strengthen governance frameworks and foster integrity-driven corporate environments. This study investigates the relationship between firm-level corruption experiences and the Corruption Perceptions Index (CPI), a widely used measure of perceived public-sector corruption. Three indicators from the World Bank Enterprise Surveys are used to capture firm-level corruption: firms’ bribery incidence, gifts to tax officials, and informal payments to public officials. The analysis covers data from 36 countries and employs a rigorous methodological approach, including mean-based estimation techniques such as Gaussian Generalized Linear Models (Gaussian GLM) and Robust Least Squares (RLS), as well as Bootstrap Quantile Regression (BQR). The Gaussian GLM and RLS results indicate that all three indicators have a significant negative impact on the CPI, meaning that more frequent occurrences of these firm-level corrupt practices are associated with lower CPI scores, which reflect higher perceived levels of corruption. The BQR analysis further reveals that the negative impact of two firm-level corruption indicators, bribery incidence and gifts to tax officials, is concentrated in the lower quantiles, indicating a stronger effect in countries with low CPI scores or higher apparent corruption. These findings underscore the importance of strengthening institutional oversight and promoting business integrity at the firm level, as reducing routine corruption in business interactions can meaningfully enhance a country’s overall corruption perception and institutional credibility.
Co-Authors Afjal, Mohd Al-Gunaid , Hala T. Ali, Najabat Amalina, Faizah Attari, Muhammad Umer Quddoos Bani, Nor Yasmin binti Mhd Bozkaya, Seyma Chairunnisa, Rizka Çoban, Mustafa Necati Dahlia, Putri Devi, N. Chitra Duta, Teuku F. Duwal, Niroj Eddy Gunawan, Eddy Emran, Talha Bin Fajri, Irfan Fazli, Qalbin Salim Fijay, Ade Habya Fitriyani Fitriyani Fredinan Yulianda Fumey, Michael Provide Furqan, Nurul Hadiyani, Rahmilia Hafizah, Iffah Hamoud, Lama MA. Hapzi Ali Hardia, Natasha Athira Keisha HUMAM, RAIS AULIA Idroes , Ghalieb M. Idroes, Ghalieb Mutig Idroes, Ghazi M. Idroes, Ghifari Maulana Idroes, Rinadi Iin Shabrina Hilal Kadri, Mirzatul Khairun Nisa Kusumo, Fitranto Lala, Andi Majid, M. Shabri Abd Majumder, Shapan Chandra Mardayanti, Ulfa Marsellindo, Rio Maulana, Aga Maulana, Ar Razy Ridha Maulidar, Putri Mirza, Muhammad Alfin Falha Mose, Naftaly Muhammad Adam, Muhammad Nghiem, Xuan-Hoa Noviandy, Teuku R. Ray, Samrat Rimal Mahdani Rinaldi Idroes Ringga, Edi Saputra Salimullah, Abul Hasnat Muhammed Saputra, Jumadil Sasmita, Novi Reandy Sikdar, Asaduzzaman Siregar, Muhammad Ilhamsyah Sofyan Syahnur Sofyan, Rahmi Souvia Rahimah Sugeng Santoso Suriani Suriani Suwal, Sunil T. Zulham Tanchev, Stoyan Taufiq Carnegie Dawood Teuku Rizky Noviandy Utami, Resty Tamara Zahriah, Zahriah