In emerging markets like Vietnam, where student borrowers often lack traditional credit histories, accurately predicting loan eligibility remains a critical yet underexplored challenge. While machine learning and deep learning techniques have shown promise in credit scoring, their comparative performance in the context of student loans has not been thoroughly investigated. This study aims to evaluate and compare the predictive effectiveness of four supervised learning models—such as Random Forest, Gradient Boosting, Support Vector Machine, and Deep Neural Network (implemented with PyTorch version 2.6.0)—in forecasting student credit eligibility. Primary data were collected from 1024 university students through structured surveys covering academic, financial, and personal variables. The models were trained and tested on the same dataset and evaluated using a comprehensive set of classification and regression metrics. The findings reveal that each model exhibits distinct strengths. Deep Learning achieved the highest classification accuracy (85.55%), while random forest demonstrated robust performance, particularly in providing balanced results across classification metrics. Gradient Boosting was effective in recall-oriented tasks, and support vector machine demonstrated strong precision for the positive class, although its recall was lower compared to other models. The study highlights the importance of aligning model selection with specific application goals, such as prioritizing accuracy, recall, or interpretability. It offers practical implications for financial institutions and universities in developing machine learning and deep learning tools for student loan eligibility prediction. Future research should consider longitudinal data, behavioral factors, and hybrid modeling approaches to further optimize predictive performance in educational finance.

Fisheries are forecasted to shrink in the tropics due to climate change. In Vietnam, fisheries are a pro-poor economic sector and essential nutrition source; however, welfares of producers and consumers in the climate change context are not well understood. While most studies focus on the gains or losses of total products and revenues, this paper pays additional attention to the changes in surpluses of market players in the long run. A combination of the production function, demand and supply functions, and partial equilibrium analysis is employed to measure the production and welfare impacts based on time series data from 1976 to 2018 and a Vietnam household living standards survey in 2018. The results show that relative to the present, catch yield is likely to reduce 35%-45% by mid-century and 45%-80% by the end of the century. Consumers may lose their surplus of 7-9 billion USD (PPP, 2018) by 2035 and 10-18 billion USD by 2065 due to supply reduction, while producers may gain additional profit of 3.5-4.5 billion USD by 2035 and 5-9 billion USD by 2065 owing to a price increase. The research findings suggest that Vietnam could impose measures to limit capture effort, as set out in the Law of Fisheries 2017, without harming fisher welfare. The expansion of aquaculture could reduce the gap between supply and demand of wild fish to mitigate consumer welfare loss; however, this impact is still ambiguous.

Waste pollution is becoming a major health issue in many developing nations. Waste-reduction options have been investigated and proposed, but environmental culture-based initiatives have not. This study explores and advances Vietnamese families’ environmental culture related to waste management, using the Culture Tower framework and a contingent valuation method coupled with a Bayesian model (CVBM). Specifically, descriptive statistics measure environmental literacy, while CVBM determines household willingness-to-pay (WTP) and estimates WTP for waste treatment services (WTP4WTS). Based on our survey of 487 households across 11 communes and wards in Hai Phong City, local waste pollution has decreased over time, although the respondents remain concerned. Over 13% of households were dissatisfied with waste treatment services (WTSs), while approximately 50% were neutral. Most respondents (79.26%) were willing to pay for improved WTSs, with an average WTP of 60,200 VND (US$2.32) per household per month. Behavioral and perceptual factors, such as the desire for improved waste services, current perceived waste pollution, and the perception that pollution has worsened, were found to significantly influence this willingness. Our study makes three major contributions. First, it develops a novel CVBM framework that links environmental culture and an economic valuation method, strengthening green economy micro-behavioral research. Second, it advances the circular economy literature by highlighting household engagement and willingness-to-pay as key drivers of sustainable waste financing and resource-loop closure. Third, it provides empirical evidence to inform and refine Vietnam’s revised Law on Environmental Protection (2020), particularly in implementing the “polluter pays” principle, promoting waste classification at the source, and designing socially acceptable environmental financing mechanisms.

Waste pollution represents an increasingly serious problem affecting the health and well-being of people living in many developing countries. Many studies have examined and recommended waste-reducing solutions, yet environmental culture-based measures remain understudied. This study employs a novel approach that integrates the Culture Tower with the Contingent Valuation Method and a Bayesian model (CVBM) to explore and advance households’ environmental culture associated with waste management. Specifically, descriptive statistics capture respondents’ environmental perceptions and literacy, while the Bayesian model and CVM identify the determinants of households’ willingness to pay (WTP) and estimate WTP for waste treatment service (WTP4WTS), respectively. We found that despite the observed reduction in local waste pollution over time, respondents maintain a persistent concern regarding this issue. Over 13% of the households surveyed expressed dissatisfaction with waste treatment services (WTS), contrasting with nearly 50% of households that reported a neutral perspective. We also found that a significant majority (79.26%) of respondents were willing to pay for WTS, with an average WTP of 60,200 VND (US$2.32) per month. Importantly, the primary predictors of WTP4WTS were found to be the desire for improved waste services, current perceived waste pollution, and the belief that pollution has worsened over time. This study makes three key contributions. First, it develops an integrated CVBM framework linking environmental culture with economic valuation, thereby strengthening the micro-behavioral foundations of green economy research. Second, it advances the circular economy literature by identifying household engagement and willingness to pay as critical drivers of sustainable waste-financing and resource-loop closure. Third, it provides empirical evidence to inform and refine the implementation of Vietnam’s revised Law on Environmental Protection (2020), particularly in operationalizing the “polluter pays” principle, promoting waste classification at source, and designing socially acceptable environmental financing mechanisms.

Valuing cultural heritage is essential for capturing non-market benefits and informing evidence-based conservation policies. This study combines the Contingent Valuation Method (CVM) and the fuzzy Analytic Hierarchy Process (FAHP) to estimate and transfer the economic value of tangible heritage within Vietnam’s Trang An Scenic Landscape Complex. The proposed approach first applies CVM to elicit visitors’ willingness to pay (WTP) for conserving the historically significant Dinh-Le Temples. Subsequently, FAHP is employed to transfer and scale these site-specific values to other cultural monuments across Trang An. On a Purchasing-Power-Parity (PPP)-adjusted basis, domestic tourists report an average WTP of VND 730,000 per visit, while international visitors indicate an average WTP of USD 26.6. Factors such as income, prior knowledge about the site, frequency of visits, and participation in heritage conservation significantly influence visitors’ WTP. Using FAHP-based value transfer, the total annual value of the complex’s cultural monuments is estimated to exceed VND 1,940 billion (approximately USD 278 million). Based on these findings, the study proposes several policy implications aimed at developing a heritage industry that integrates conservation, creativity, and controlled commercialization, thus positioning Trang An’s cultural assets as drivers of sustainable economic development.