Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecas...Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.展开更多
Due to information asymmetry and strategic innovation,firms often encounter challenges related to insufficient driving forces and low-quality innovation outcomes.Analysts always act as information intermediaries who h...Due to information asymmetry and strategic innovation,firms often encounter challenges related to insufficient driving forces and low-quality innovation outcomes.Analysts always act as information intermediaries who help foster the advancement of corporate innovation activities and the conversion of innovation output.This study examines the impact of analyst coverage and forecasting bias on corporate innovation,employing data from China A-shared listed firms spanning the period 2007 to 2019.We measure corporate innovation from two perspectives:Input and output.Specifically,we use the ratio of research and development(R&D)expenditure to sales as a proxy for the innovation input and the number of patent citations excluding self-citations to measure innovation output.We find that analyst coverage promotes corporate innovation,which is consistent with the“bright”side of analyst coverage.However,the positive effect of analyst coverage hinges on effectively transmitting and disclosing accurate information to investors in the capital market.Based on this,analysts'forecasting bias includes forecasting dispersion and optimism bias.We find evidence that an increase in analysts'forecast dispersion leads to a decrease in corporate innovation quality.Moreover,this paper presents a novel approach by employing the regression discontinuity method to examine the effect of analyst optimistic bias on firm innovation.The empirical findings reveal that overly optimistic forecasts by analysts exacerbate innovation quality.These analyses enrich the research on analyst coverage and corporate innovation,providing an empirical basis for improving the capital market with the help of analysts.展开更多
This study examines the relationship between analyst forecast dispersion or accuracy and supplier concentration of listed firms in China from 2008 to 2019.Our findings suggest that higher supplier concentration is ass...This study examines the relationship between analyst forecast dispersion or accuracy and supplier concentration of listed firms in China from 2008 to 2019.Our findings suggest that higher supplier concentration is associated with lower analyst forecast dispersion,which can be attributed to the increased attention from analysts.Moreover,this effect is more pronounced when firms have less bargaining power and higher institutional ownership,indicating a greater reliance on the supply chain.Our study highlights the importance of disclosing supply chain information,which provides insights beyond those of traditional financial information.展开更多
基金the National Key Research and Development Plan of China[Grant No.2023YFB3002400]the Shanghai 2021 Natural Science Foundation[Grant Nos.21ZR1420400 and 21ZR1419800]+1 种基金the Shanghai 2023 Natural Science Foundation[Grant No.23ZR1463000]the Shandong Provincial Meteorological Bureau Scientific Research Project[Grant No.2023SDBD05].
文摘Accurate short-term forecast of offshore wind fields is still challenging for numerical weather prediction models.Based on three years of 48-hour forecast data from the European Centre for Medium-Range Weather Forecasts Integrated Forecasting System global model(ECMWF-IFS)over 14 offshore weather stations along the coast of Shandong Province,this study introduces a multi-task learning(MTL)model(TabNet-MTL),which significantly improves the forecast bias of near-surface wind direction and speed simultaneously.TabNet-MTL adopts the feature engineering method,utilizes mean square error as the loss function,and employs the 5-fold cross validation method to ensure the generalization ability of the trained model.It demonstrates superior skills in wind field correction across different forecast lead times over all stations compared to its single-task version(TabNet-STL)and three other popular single-task learning models(Random Forest,LightGBM,and XGBoost).Results show that it significantly reduces root mean square error of the ECMWF-IFS wind speed forecast from 2.20 to 1.25 m s−1,and increases the forecast accuracy of wind direction from 50%to 65%.As an explainable deep learning model,the weather stations and long-term temporal statistics of near-surface wind speed are identified as the most influential variables for TabNet-MTL in constructing its feature engineering.
文摘Due to information asymmetry and strategic innovation,firms often encounter challenges related to insufficient driving forces and low-quality innovation outcomes.Analysts always act as information intermediaries who help foster the advancement of corporate innovation activities and the conversion of innovation output.This study examines the impact of analyst coverage and forecasting bias on corporate innovation,employing data from China A-shared listed firms spanning the period 2007 to 2019.We measure corporate innovation from two perspectives:Input and output.Specifically,we use the ratio of research and development(R&D)expenditure to sales as a proxy for the innovation input and the number of patent citations excluding self-citations to measure innovation output.We find that analyst coverage promotes corporate innovation,which is consistent with the“bright”side of analyst coverage.However,the positive effect of analyst coverage hinges on effectively transmitting and disclosing accurate information to investors in the capital market.Based on this,analysts'forecasting bias includes forecasting dispersion and optimism bias.We find evidence that an increase in analysts'forecast dispersion leads to a decrease in corporate innovation quality.Moreover,this paper presents a novel approach by employing the regression discontinuity method to examine the effect of analyst optimistic bias on firm innovation.The empirical findings reveal that overly optimistic forecasts by analysts exacerbate innovation quality.These analyses enrich the research on analyst coverage and corporate innovation,providing an empirical basis for improving the capital market with the help of analysts.
基金support from the National Natural Science Foundation of China(No.72103217).
文摘This study examines the relationship between analyst forecast dispersion or accuracy and supplier concentration of listed firms in China from 2008 to 2019.Our findings suggest that higher supplier concentration is associated with lower analyst forecast dispersion,which can be attributed to the increased attention from analysts.Moreover,this effect is more pronounced when firms have less bargaining power and higher institutional ownership,indicating a greater reliance on the supply chain.Our study highlights the importance of disclosing supply chain information,which provides insights beyond those of traditional financial information.
