Claim Missing Document
Check
Articles

Found 3 Documents
Search

An Interpretable Machine Learning Framework for Imbalanced Audit Opinion Prediction Ha Thanh Nguyen
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.v7i3.1373

Abstract

Audit opinion prediction is important for capital-market monitoring because non-unqualified audit opinions may signal financial distress, reporting uncertainty, and elevated information risk. This study develops an interpretable machine learning framework for predicting non-unqualified audit opinions under severe class imbalance using firm-year observations of Vietnamese listed companies from 2015 to 2024. The proposed framework is based on a Modified Random Forest approach that integrates imbalance-aware sub-sampling, performance-based tree selection, ensemble probability aggregation, and decision-rule extraction. The framework is designed to improve minority-class detection while preserving transparent and economically interpretable risk signals. The empirical analysis compares the proposed framework with several benchmark models, including logistic regression, Support Vector Machine, k-nearest neighbours, Random Forest, XGBoost, Random Forest with synthetic minority oversampling, cost-sensitive Random Forest, and Balanced Random Forest. Predictive performance is evaluated using three validation strategies: a random 70/30 train-test split, an out-of-time split in which observations from 2015-2021 are used for training and observations from 2022-2024 are reserved for testing, and k-fold cross-validation. The proposed framework achieves the strongest overall performance across these settings, with area under the receiver operating characteristic curve values of 0.829, 0.811, and 0.793, respectively, while also improving minority-class recall and F1-score relative to benchmark models. The extracted decision rules indicate that audit opinion modifications are associated with persistent and interacting financial vulnerabilities, particularly prior modified opinions, weak profitability, leverage pressure, limited debt-servicing capacity, liquidity constraints, and asset-structure risk. Methodologically, the study contributes by integrating imbalance-aware ensemble learning with interpretable rule-based analysis. Practically, the framework may serve as a complementary early-warning tool for auditors, regulators, and investors in financial reporting risk assessment within emerging markets.
Applying the Smooth Transition Autoregressive Model for Discovering the Nonlinear Cointegration Relationship Between the Interest Rate and Inflation in Vietnam Ha Thanh Nguyen
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.568

Abstract

Interest rates and inflation are two key macroeconomic indicators that have a direct impact on a country’s economy. The Fisher hypothesis addresses the relationship between these two variables, with its core idea being that nominal interest rates and inflation have a positive long-term relationship, while real interest rates remain constant. The primary objective of this study is to explore the relationship between interest rates and inflation in Vietnam during the period from 2007 to 2023. Unlike previous studies, this research, based on Vietnam's specific context, employs the Smooth Transition Autoregressive (STAR) model. This approach allows for testing nonlinear cointegration, overcoming the limitations of traditional cointegration methods. The study identifies that interest rates and inflation exhibit long-term co-movement, adhering to a common trend. When these two variables deviate from their equilibrium position, they rapidly adjust back to equilibrium, governed by an asymmetric logarithmic transition function. The findings challenge the one-to-one relationship proposed by the Fisher hypothesis, revealing a more complex link between interest rates and inflation. Additionally, the study highlights the interactive nature of Vietnam’s monetary and financial markets. It demonstrates that monetary policy tools can influence the financial market, while the long-term nominal interest rate emerges as a potential indicator of inflation. These insights provide significant implications for policymakers aiming to stabilize the economy through effective monetary and financial strategies. This research further confirms the effectiveness of nonlinear cointegration methods and the STAR model in macroeconomic analysis. The article also presents an interesting finding regarding the Fisher hypothesis in a developing country like Vietnam.
An Interpretable Machine Learning Framework for Imbalanced Audit Opinion Prediction Ha Thanh Nguyen
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.v7i3.1373

Abstract

Audit opinion prediction is important for capital-market monitoring because non-unqualified audit opinions may signal financial distress, reporting uncertainty, and elevated information risk. This study develops an interpretable machine learning framework for predicting non-unqualified audit opinions under severe class imbalance using firm-year observations of Vietnamese listed companies from 2015 to 2024. The proposed framework is based on a Modified Random Forest approach that integrates imbalance-aware sub-sampling, performance-based tree selection, ensemble probability aggregation, and decision-rule extraction. The framework is designed to improve minority-class detection while preserving transparent and economically interpretable risk signals. The empirical analysis compares the proposed framework with several benchmark models, including logistic regression, Support Vector Machine, k-nearest neighbours, Random Forest, XGBoost, Random Forest with synthetic minority oversampling, cost-sensitive Random Forest, and Balanced Random Forest. Predictive performance is evaluated using three validation strategies: a random 70/30 train-test split, an out-of-time split in which observations from 2015-2021 are used for training and observations from 2022-2024 are reserved for testing, and k-fold cross-validation. The proposed framework achieves the strongest overall performance across these settings, with area under the receiver operating characteristic curve values of 0.829, 0.811, and 0.793, respectively, while also improving minority-class recall and F1-score relative to benchmark models. The extracted decision rules indicate that audit opinion modifications are associated with persistent and interacting financial vulnerabilities, particularly prior modified opinions, weak profitability, leverage pressure, limited debt-servicing capacity, liquidity constraints, and asset-structure risk. Methodologically, the study contributes by integrating imbalance-aware ensemble learning with interpretable rule-based analysis. Practically, the framework may serve as a complementary early-warning tool for auditors, regulators, and investors in financial reporting risk assessment within emerging markets.