Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise info...Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment scenario.First,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise information.The proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model updating.Secondly,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and interpretability.In addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global model.The results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify defaulters.Finally,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.展开更多
Micro and small enterprises （MSEs） are considered the most dynamic and flexible arrangement of activity. In the economy, the foundation and development of these features is important for the creation of the so-call...Micro and small enterprises （MSEs） are considered the most dynamic and flexible arrangement of activity. In the economy, the foundation and development of these features is important for the creation of the so-called ＂normal＂ economic environment. The main objective of this research is to present a research model of innovation in MSEs to analyse： first, the degree of innovation of MSEs, and second, how the innovation is handled by existing MSEs as a result of its business environment. The research made is based on a sample of 550 MSEs distributed over six cities across the Brazilian State of Piaui. The data were collected using the Innovation Radar application, which is owned by the SEBRAE Local Innovation Agents program. Statistical techniques of descriptive, exploratory, and inferential nature were used for corresponding data treatment and results validation. The results obtained suggest that MSEs have innovation capacity between the ＂Little Innovative＂ and ＂Occasional Innovative＂ range, and also that the average and the distribution of innovation levels are similar amongst MSEs analyzed.展开更多
基金funded by the State Grid Jiangsu Electric Power Company(Grant No.JS2020112)the National Natural Science Foundation of China(Grant No.62272236).
文摘Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment scenario.First,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise information.The proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model updating.Secondly,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and interpretability.In addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global model.The results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify defaulters.Finally,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.
文摘Micro and small enterprises （MSEs） are considered the most dynamic and flexible arrangement of activity. In the economy, the foundation and development of these features is important for the creation of the so-called ＂normal＂ economic environment. The main objective of this research is to present a research model of innovation in MSEs to analyse： first, the degree of innovation of MSEs, and second, how the innovation is handled by existing MSEs as a result of its business environment. The research made is based on a sample of 550 MSEs distributed over six cities across the Brazilian State of Piaui. The data were collected using the Innovation Radar application, which is owned by the SEBRAE Local Innovation Agents program. Statistical techniques of descriptive, exploratory, and inferential nature were used for corresponding data treatment and results validation. The results obtained suggest that MSEs have innovation capacity between the ＂Little Innovative＂ and ＂Occasional Innovative＂ range, and also that the average and the distribution of innovation levels are similar amongst MSEs analyzed.
