RESUMO
This paper develops an artificial intelligence based automated valuation model (AI-AVM) using the boosting tree ensemble technique to predict housing prices in Singapore. We use more than 300,000 private and public housing transactions in Singapore for the period from 1995 to 2017 in the training of the AI-AVM models. The boosting model is the best predictive model that produce the most robust and accurate predictions for housing prices compared to the decision tree and multiple regression analysis (MRA) models. The boosting AI-AVM models explain 91.33% and 94.28% of the price variances, and keep the mean absolute percentage errors at 8.55% and 5.34% for the public housing market and the private housing market, respectively. When subject the AI-AVM to the out-of-sample forecasting using the 2018 housing sale samples, the prediction errors remain within a narrow range of between 5% and 9%.
RESUMO
This paper examines the long-term effects of birth cohort size on life outcomes. Using administrative data from Singapore, we study the outcomes of large birth cohorts created by the Chinese superstitious practice of zodiac birth timing, where parents prefer to give birth in the year of the Dragon. This practice is followed exclusively by the Chinese majority, with no similar patterns detected among non-Chinese minorities, allowing us to differentiate cohort size effects from confounding year-of-birth effects. Despite government efforts to increase public educational resources for these cohorts, Chinese Dragons earn lower incomes and are less likely to gain admission to national universities. There is also evidence of negative externalities on non-practising populations who happen to enter the labour market at the same time as Chinese Dragons. Our analysis suggests that the adverse life outcomes are not due to selection, but rather reflect the aggregate resource implications of birth cohort size.Supplementary material is available for this article at: https://doi.org/10.1080/00324728.2020.1864458.
RESUMO
Agglomeration of firms significantly increases pollution emission intensity and brings unintended consequences to public health. We develop the pollution emission indices using the firm-level pollutant emission data in China to track pollution intensities at the source using the locally weighted regression approach. Our constant-quality pollutant emission indices for three pollutants (wastewater discharge, COD, and SO2) and the pollution emission heatmaps show decreasing trends for the three pollutants from 1998 to 2012. We also show significant spatial clustering and regional variations in pollution emission trends. Industrial pollution mitigations in China's Eastern and Central regions have been neglected for decades since 2021, when driving economic growth took priority. The regime shifts in pollution controls from the 10th (2000-2005) to the 11th (2006-2010) Five-Year Plan period show the effects of tightening pollution emission controls. Failure to cut pollution emissions at source causes health consequences to residents living and working in nearby polluting industries. The latent environmental hazard could be a ticking time bomb, which could not be delinked from the emergence of cancer villages in the regions. Therefore, enforcing strict and uniform pollution controls and setting clear emission limits at sources can eliminate free-rider problems by polluting firms.