Predicting accounting fraud using imbalanced ensemble learning classifiers – evidence from China

The current research aims to launch effective accounting fraud detection models using imbalanced ensemble learning algorithms for China A-Share listed firms. Based on a sample of 33,544 Chinese firm-year instances from 1998 to 2017, this research respectively established one logistic regression and four ensemble learning classifiers (AdaBoost, XGBoost, CUSBoost, and RUSBoost) by 12 financial ratios and 28 raw financial data. Additionally, we divided the sample into the train and test observations to evaluate the classifiers' out-of-sample performance. In detail, we applied two metrics, namely, Area under the ROC (receiver operating characteristic) curve (AUC) and Area under the Precision-Recall curve (AUPR), to evaluate classifiers' discriminability. In the supplement test, this study put forward an algebraic fused model on the basis of the four ensemble learning classifiers and introduced the sliding window technique. The empirical results showed that the ensemble learning classifiers can detect accounting fraud for the imbalanced China A-listed firms far more effectively than the logistic regression model. Moreover, imbalanced ensemble learning classifiers (CUSBoost and RUSBoost) effectively performed better than the common ensemble learning models (AdaBoost and XGBoost) in average. The algebraic fused model in the supplement test also obtained the highest average AUC and AUPR among all the employed algorithms. Our results offer firm support for the potential role of Machine Learning (ML)-based Artificial Intelligence (AI) approaches in reliably predicting accounting fraud with high accuracy. Similarly, for the Chinese settings, our ML-based AI offers utmost advantage in forecasting accounting fraud. Finally, this paper fills the research gap on the applications of imbalanced ensemble learning in accounting fraud detection for Chinese listed firms.     

Capitalised nonmarket benefits of multifunctional water-sensitive urban infrastructure: A case of living streams

Living streams are an important element of decentralised stormwater management solutions. They are actively promoted due to their ability to generate multiple ecosystem services, including water quality improvement, biodiversity protection and aesthetics. However, a lack of monetised values of ecosystem services of living stream projects makes it difficult to assess the net benefits of investing in such projects. This study uses the hedonic pricing method to estimate the capitalised amenity values of living streams and other public open spaces (POS) in housing and lot markets for the first time. The study area includes two newly greenfield-developed suburbs in the Perth metropolitan area. We find the positive impact of living streams and other POS on the house and lot prices. However, living streams generate greater value than other types of POS. Furthermore, the POS (including living streams) that support active recreation are valued more than basic POS without active recreation features. Finally, we observe, for the first time, that the benefits of planned but not yet constructed POS (including living stream) are similar to the completed POS (including living stream) in both housing and lot markets. This information is useful for policymakers and developers making informed decisions about water-sensitive urban infrastructure.     

Structural changes and economic landscape of the Indian economy: 2000-2019

This study employs input-output analysis to determine the extent of structural changes in the Indian economy, as well as how economic sector linkages changed between 2000 and 2019, and identifies the sectors with profound linkages with other sectors.  Furthermore, we use the causative matrix to examine the temporal changes in intersectoral interactions. The analysis shows that manufacturing sectors have stronger intersectoral linkages than sevice sectors, with resource-intensive and scale-intensive manufacturing sectors having the most profound linkages. Furthermore, the causative matrix analysis reveals that Indian sectors became more externalized following the global financial crises, while receiving less feedback from other sectors. The results suggest that intersectoral linkages should be taken into account when designing industrial policies, and that investment should be encouraged in India's key economic sectors.     

Social capital and capital allocation efficiency

Based on the social norms and structural theories of social capital, this study examines the relationship between community social capital and the firms’ capital allocation efficiency. We hypothesize and find that the community social capital of a firm's headquarter area has a negative and statistically significant impact on its capital allocation inefficiency, which is robust to alternative proxies for community social capital and capital allocation inefficiency, propensity score matching and instrumental variable regressions. In addition, we find that the effect of community social capital is more pronounced for firms with poor internal ethical culture and weak network connections to outside executives and directors, implying that community social capital becomes important in these situations. This finding links prior social norms and networks literature to capital allocation studies in that the norms and networks components of community social capital discipline self-interested managers’ behavior and reduce information asymmetry-two channels of capital allocation efficiency. Overall, community social capital works as a compensatory monitoring and information transfer mechanism and improves the firms’ capital allocation efficiency.     

Rural Bangladeshi consumers’ (un)willingness to pay for low-milled rice: Implications for zinc biofortification

Zinc deficiency is a severe public health problem in Bangladesh. We examine the effects of nutritional information on rural consumers’ willingness-to-pay (WTP) for two ways to increase zinc intake through rice, the main staple crop–low-milling that gives rice grains a distinctive light brown color (a visible trait) and sets it apart from the culturally preferred high-milled white rice grain and biofortification of rice with increased zinc content (an invisible trait), which is also low-milled to retain maximum zinc content. Results of our economic experiments suggest that with nutritional information, consumers are willing to pay a premium of 4.6% for zinc biofortified rice compared to non-biofortified rice, when milled at the same level. However, results confirm the strong preference for high-milled rice by Bangladeshi consumers who discounted low-milled rice by 8%–10% even after receiving information on the nutritional benefits of biofortified or low-milled rice. We find that consumers’ WTP for the two high-zinc-low-milled rice types (biofortified and non-biofortified) is positively correlated with being a female, more educated, belonging to households engaged in non-farm activities and with children under 5 years of age. Results point to the importance of nutritional awareness campaigns for increasing zinc biofortified and low-milled rice consumption and guiding the targeting strategy for such campaigns. Given the consumer preference for high-milled rice, this study also points to the need for exploring the rice fortification strategy to address the challenge of malnutrition.     

The role of liquidity in monetary policy transmission: Evidence from Indian banks1

The role of bank liquidity in monetary policy transmission has received insufficient attention in the literature. Faced with monetary tightening, banks with more liquidity can sell off securities and protect their loan portfolios. We test this proposition using panel data for Indian banks during 2005–2020. Employing dynamic threshold panel regressions with liquid assets as the threshold variable, we show that bank lending declines with monetary policy tightening in low liquidity regimes, but not in high liquidity regimes. We also find evidence for different portfolio reallocation behaviour by banks in high versus low liquidity regimes in response to monetary policy changes.