Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00089
Xianke Li
As a subversive technology, artificial intelligence will promote the transformation of commercial banks to intelligence. At present, technologies such as speech recognition and integrated learning have been applied in the banking industry, such as intelligent response robot, personalized application experience and service, etc. Commercial banks have also set up big data teams to use machine learning and predictive analysis technology for customer group portrait and risk early warning. In the future, AI related technologies will be applied to more scenarios such as risk control, credit decision-making, insurance pricing, service recommendation and customer service to further optimize the back-end and front-end business of commercial banks and improve operational efficiency.
{"title":"Application and influence of artificial intelligence technology in commercial banks","authors":"Xianke Li","doi":"10.1109/ICCSMT54525.2021.00089","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00089","url":null,"abstract":"As a subversive technology, artificial intelligence will promote the transformation of commercial banks to intelligence. At present, technologies such as speech recognition and integrated learning have been applied in the banking industry, such as intelligent response robot, personalized application experience and service, etc. Commercial banks have also set up big data teams to use machine learning and predictive analysis technology for customer group portrait and risk early warning. In the future, AI related technologies will be applied to more scenarios such as risk control, credit decision-making, insurance pricing, service recommendation and customer service to further optimize the back-end and front-end business of commercial banks and improve operational efficiency.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129512093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00017
Huaijin Shi, Gao Yuan, Zhuoran Lu, Qian Liang
The prediction of stock price is a popular and difficult topic that attracted and confused many investors over a long period of time. Because of the complex transaction market, there are a lot of risks when we do transactions. Until now, there are two schools about the stock market forecasting: fundamental analysis and technical analysis. The topic of this paper is to use the Recurrent Neural Networks to predict the stock price of Apple Inc in the future. In addition, the important unit of our RNN is Long Short-term Memory (LSTM), which introduces the memory cell, replacing traditional artificial neurons in the hidden layer of the network. Our Networks are able to associate memories and input remote in time, which could grasp the structure of data dynamically over time with high prediction capacity. To visualize our results, we draw three figures. We evaluated our model's performance on the dataset provided by the kaggle competition. The results of the experiment show that our method achieves a good performance compared with other machine learning methods. The RMSE of our model is 0.66 and 0.39 smaller than ridge regression and the neural network model respectively.
{"title":"LSTM Based Model For Apple Inc Stock Price Forecasting","authors":"Huaijin Shi, Gao Yuan, Zhuoran Lu, Qian Liang","doi":"10.1109/ICCSMT54525.2021.00017","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00017","url":null,"abstract":"The prediction of stock price is a popular and difficult topic that attracted and confused many investors over a long period of time. Because of the complex transaction market, there are a lot of risks when we do transactions. Until now, there are two schools about the stock market forecasting: fundamental analysis and technical analysis. The topic of this paper is to use the Recurrent Neural Networks to predict the stock price of Apple Inc in the future. In addition, the important unit of our RNN is Long Short-term Memory (LSTM), which introduces the memory cell, replacing traditional artificial neurons in the hidden layer of the network. Our Networks are able to associate memories and input remote in time, which could grasp the structure of data dynamically over time with high prediction capacity. To visualize our results, we draw three figures. We evaluated our model's performance on the dataset provided by the kaggle competition. The results of the experiment show that our method achieves a good performance compared with other machine learning methods. The RMSE of our model is 0.66 and 0.39 smaller than ridge regression and the neural network model respectively.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130875097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00082
Hong Yan, Xinyue Ma, Shengwen He
The purpose of this paper is to solve the problem of intelligent analysis of learners' behavior and intelligent recommendation in the domain of medical online education. The teaching behavior has transformed from experience teaching into massive data teaching. Moreover, the learning behavior is also changed from centralized learning to fragmented learning. In this paper, we study the method of personal education recommendation to meet these challenges. In this paper, a novel multi-view extreme learning machine model is proposed. We can get the optimized classification results. Based on these results, we proposed a collaborative filtering based personal recommendation method and applied via Spark framework. The experimental results show that, based on the effective analysis of learning behavior, the proposed method can be used to recommend the medical online learning content for the learners in practical teaching. In this paper, data mining and recommendation methods are realized in the field of medical online education. The methodological research and case studies can meet the needs of medical online education.
{"title":"Research on Real-time Medical Online Learning Content Recommendation based on Multi-view Data Mining","authors":"Hong Yan, Xinyue Ma, Shengwen He","doi":"10.1109/ICCSMT54525.2021.00082","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00082","url":null,"abstract":"The purpose of this paper is to solve the problem of intelligent analysis of learners' behavior and intelligent recommendation in the domain of medical online education. The teaching behavior has transformed from experience teaching into massive data teaching. Moreover, the learning behavior is also changed from centralized learning to fragmented learning. In this paper, we study the method of personal education recommendation to meet these challenges. In this paper, a novel multi-view extreme learning machine model is proposed. We can get the optimized classification results. Based on these results, we proposed a collaborative filtering based personal recommendation method and applied via Spark framework. The experimental results show that, based on the effective analysis of learning behavior, the proposed method can be used to recommend the medical online learning content for the learners in practical teaching. In this paper, data mining and recommendation methods are realized in the field of medical online education. The methodological research and case studies can meet the needs of medical online education.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116969162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00113
Chengcheng Zhu, Lie Feng
The excess capacity caused by the herd behavior of enterprise investment is one of the important problems that contribute to the waste of domestic resources and environmental pollution. Based on the big data of the whole industry of listed companies in Shanghai and Shenzhen A-shares from 2008 to 2020, this paper explores the impact of public environmental protection on corporate investment behavior. The results show that: (1) public environmental protection can significantly inhibit the herd behavior of enterprise investment; (2) When the degree of regional marketization is higher, the inhibition effect of public environmental protection is stronger; (3) The inhibition effect of public participation in environmental protection is stronger when management shares. In this paper, further tests were carried out by controlling the sample range, controlling endogeneity and changing the measurement method of indicators, and the results were still robust. This paper enriches the research on external governance mechanism of enterprise investment behavior, and tries to discuss the dual role of internal and external governance, and has certain policy significance.
{"title":"How Does Public Environmental Protection Restrain Enterprise Overcapacity?-Empirical Analysis Based on Big Data of Chinese Listed Companies","authors":"Chengcheng Zhu, Lie Feng","doi":"10.1109/ICCSMT54525.2021.00113","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00113","url":null,"abstract":"The excess capacity caused by the herd behavior of enterprise investment is one of the important problems that contribute to the waste of domestic resources and environmental pollution. Based on the big data of the whole industry of listed companies in Shanghai and Shenzhen A-shares from 2008 to 2020, this paper explores the impact of public environmental protection on corporate investment behavior. The results show that: (1) public environmental protection can significantly inhibit the herd behavior of enterprise investment; (2) When the degree of regional marketization is higher, the inhibition effect of public environmental protection is stronger; (3) The inhibition effect of public participation in environmental protection is stronger when management shares. In this paper, further tests were carried out by controlling the sample range, controlling endogeneity and changing the measurement method of indicators, and the results were still robust. This paper enriches the research on external governance mechanism of enterprise investment behavior, and tries to discuss the dual role of internal and external governance, and has certain policy significance.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131380148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00071
Jie Yuan, Shuo Chen, Zhaoyi Shi, Shaona Yu
Currently, tracking methods based on discriminative correlation filter and Siamese network are one of the hot research topics in visual object tracking tasks. Among them, how to make full use of the rich spatio-temporal information of the target between frames in a video sequence is one of the core problems in studying this topic. To address this problem, the information related to the target in the first frame, the history frame, and the current frame is transformed throughout the tracking process with the Cross-Attention mechanism as the core mechanism, and the Siamese-like architecture is used to achieve a more complete characterization of the tracking target features. We propose a discriminative correlation filter tracking algorithm with Transformer based on a multi-frame Cross-attention mechanism to improve tracking accuracy while maintaining the tracking speed essentially constant. We tested our proposed model on GOT-10k, TrackingNet and OTB2015 datasets, and the test results demonstrate the effectiveness of our proposed model, improving tracking accuracy while running at real-time speed.
{"title":"Discriminative correlation filter tracking algorithm with Transformer based on a multi-frame Cross-Attention mechanism","authors":"Jie Yuan, Shuo Chen, Zhaoyi Shi, Shaona Yu","doi":"10.1109/ICCSMT54525.2021.00071","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00071","url":null,"abstract":"Currently, tracking methods based on discriminative correlation filter and Siamese network are one of the hot research topics in visual object tracking tasks. Among them, how to make full use of the rich spatio-temporal information of the target between frames in a video sequence is one of the core problems in studying this topic. To address this problem, the information related to the target in the first frame, the history frame, and the current frame is transformed throughout the tracking process with the Cross-Attention mechanism as the core mechanism, and the Siamese-like architecture is used to achieve a more complete characterization of the tracking target features. We propose a discriminative correlation filter tracking algorithm with Transformer based on a multi-frame Cross-attention mechanism to improve tracking accuracy while maintaining the tracking speed essentially constant. We tested our proposed model on GOT-10k, TrackingNet and OTB2015 datasets, and the test results demonstrate the effectiveness of our proposed model, improving tracking accuracy while running at real-time speed.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"329 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123662319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00088
Lan Li, Wenjuan Ren, Xiaofeng Zhang
In recent years, China has formulated a strategic plan to revitalize the development of manufacturing industry, and the state has issued many tax policies to support the development of manufacturing industry. From the perspective of taxes, this paper combs the relevant literature of manufacturing tax policy, and constructs the PMC-AE index evaluation model by adding self coding neural network technology on the basis of traditional PMC, in which 9 primary variables and 34 secondary variables are set to quantitatively evaluate the tax policy of manufacturing transformation and upgrading in Northeast China. It is found that China's current manufacturing tax policy is more reasonable, but there are still deficiencies. We should improve the manufacturing tax policy from the aspects of receptor scope, guarantee incentive form and duration, so as to provide theoretical support for the revision and optimization of the new round of policy.
{"title":"Research on Manufacturing Tax Policy Based on Neural Network","authors":"Lan Li, Wenjuan Ren, Xiaofeng Zhang","doi":"10.1109/ICCSMT54525.2021.00088","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00088","url":null,"abstract":"In recent years, China has formulated a strategic plan to revitalize the development of manufacturing industry, and the state has issued many tax policies to support the development of manufacturing industry. From the perspective of taxes, this paper combs the relevant literature of manufacturing tax policy, and constructs the PMC-AE index evaluation model by adding self coding neural network technology on the basis of traditional PMC, in which 9 primary variables and 34 secondary variables are set to quantitatively evaluate the tax policy of manufacturing transformation and upgrading in Northeast China. It is found that China's current manufacturing tax policy is more reasonable, but there are still deficiencies. We should improve the manufacturing tax policy from the aspects of receptor scope, guarantee incentive form and duration, so as to provide theoretical support for the revision and optimization of the new round of policy.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123690937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00072
H. Qi, Xiaoyan Fu, Xuejie He, Honghong Liu
In order to solve the issue of missed detection that is easy to occur in the multi object tracking algorithm FairMOT when the target appearance is similar to the background, and to improve the accuracy of multi-object tracking algorithm in pedestrian tracking, we proposed a pedestrian tracking algorithm termed as DA_FairMOT, based on FairMOT algorithm. At different levels of its feature extraction network DLA34, we added two self-attention modules, the spatial module and channel module. DA_FairMOT combined the two attention feature maps to further improve the representational capability of the model. In the experiment, we use the CLEAR MOT evaluation metric. As a result, the proposed DA_FairMOT algorithm improves IDP (the ID precision) by 1.59% on the MOT17 dataset, compared with the benchmark FairMOT algorithm. DA_FairMOT achieves 66.44 for MOTA, and 70.03 for IDF1.
{"title":"A Multiple Object Tracking Method Based on Optimized FairMOT","authors":"H. Qi, Xiaoyan Fu, Xuejie He, Honghong Liu","doi":"10.1109/ICCSMT54525.2021.00072","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00072","url":null,"abstract":"In order to solve the issue of missed detection that is easy to occur in the multi object tracking algorithm FairMOT when the target appearance is similar to the background, and to improve the accuracy of multi-object tracking algorithm in pedestrian tracking, we proposed a pedestrian tracking algorithm termed as DA_FairMOT, based on FairMOT algorithm. At different levels of its feature extraction network DLA34, we added two self-attention modules, the spatial module and channel module. DA_FairMOT combined the two attention feature maps to further improve the representational capability of the model. In the experiment, we use the CLEAR MOT evaluation metric. As a result, the proposed DA_FairMOT algorithm improves IDP (the ID precision) by 1.59% on the MOT17 dataset, compared with the benchmark FairMOT algorithm. DA_FairMOT achieves 66.44 for MOTA, and 70.03 for IDF1.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"400 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116332466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00067
Jie Yuan, Zhaoyi Shi, Shuo Chen, Shaona Yu
Feature fusion of spatial and semantic information is important to achieve high-performance semantic segmentation. However, fast semantic segmentation demands low computational complexity and challenges researchers to design structures efficiently. In recent years, Neural Network Architecture Search (NAS) has achieved better results in automatic network design. For lower computational complexity, we propose a multi-layer feature fusion with fewer connections in search space and add an improved penalty term for the loss function of the search algorithm to decrease the number of feature fusion connections. Based on the proposed multi-layer feature fusion method, we search the two-branch semantic segmentation model using the search algorithm reported by Gao's MTL-NAS. The experimental results tested on the Cityscapes dataset show that the searched module can improve the accuracy. For FastSCNN, ContextNet and BiSeNet, the mIoU improvement is 2%, 2.5% and 1%, respectively. The searched module is also more efficient than the densely connected structure.
{"title":"Multi-layer Feature Fusion Method with Fewer Connections for Fast Semantic Segmentation","authors":"Jie Yuan, Zhaoyi Shi, Shuo Chen, Shaona Yu","doi":"10.1109/ICCSMT54525.2021.00067","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00067","url":null,"abstract":"Feature fusion of spatial and semantic information is important to achieve high-performance semantic segmentation. However, fast semantic segmentation demands low computational complexity and challenges researchers to design structures efficiently. In recent years, Neural Network Architecture Search (NAS) has achieved better results in automatic network design. For lower computational complexity, we propose a multi-layer feature fusion with fewer connections in search space and add an improved penalty term for the loss function of the search algorithm to decrease the number of feature fusion connections. Based on the proposed multi-layer feature fusion method, we search the two-branch semantic segmentation model using the search algorithm reported by Gao's MTL-NAS. The experimental results tested on the Cityscapes dataset show that the searched module can improve the accuracy. For FastSCNN, ContextNet and BiSeNet, the mIoU improvement is 2%, 2.5% and 1%, respectively. The searched module is also more efficient than the densely connected structure.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116062681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00100
M. Xie, Yu Wei, Yanna Wang
These years have witnessed overcapacity of blockchains caused by low demand implementation and the lack of product usability. The excessive inventory increases the inventory cost, and reduces the value of the whole ecosystem of the supply chain. As the blockchain technology develops and matures, information systems of each link in the supply chain, including the supplier, the manufacturer, the retailer, and the logistics are able to log the information onto the chain to realize real-time tracking and collaboration. Besides, the supply chain built on the blockchain technology is more dynamic and flexible. In the present work, a three-layer supply chain model consists of a blockchain technology layer, a network layer, and an application layer to achieve real-time information sharing and collaboration of enterprises at different links of supply chain, and to increase the accuracy of demand forests and capacity of inventory replenishment, reduce supply chain risk, establishing a trust management mechanism, and unveil the principles underlying the efficiency of applying blockchain technology to control risks involved in supply chain.
{"title":"Research on Application of Blockchains in Supply Chain Risk Management","authors":"M. Xie, Yu Wei, Yanna Wang","doi":"10.1109/ICCSMT54525.2021.00100","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00100","url":null,"abstract":"These years have witnessed overcapacity of blockchains caused by low demand implementation and the lack of product usability. The excessive inventory increases the inventory cost, and reduces the value of the whole ecosystem of the supply chain. As the blockchain technology develops and matures, information systems of each link in the supply chain, including the supplier, the manufacturer, the retailer, and the logistics are able to log the information onto the chain to realize real-time tracking and collaboration. Besides, the supply chain built on the blockchain technology is more dynamic and flexible. In the present work, a three-layer supply chain model consists of a blockchain technology layer, a network layer, and an application layer to achieve real-time information sharing and collaboration of enterprises at different links of supply chain, and to increase the accuracy of demand forests and capacity of inventory replenishment, reduce supply chain risk, establishing a trust management mechanism, and unveil the principles underlying the efficiency of applying blockchain technology to control risks involved in supply chain.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"645 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123215476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1109/ICCSMT54525.2021.00090
Jinmin Zhang, Xufang Li, Dijun Fan
The influencing factors of the minimum wage play an important role in the formulation of the minimum wage, and the minimum wage has a great impact on people's livelihood. Based on the data from 2001 to 2020, this paper uses factor analysis and LASSO regression to explore the influencing factors of minimum wage in Zhejiang Province, Shanxi Province, Guizhou Province and Qinghai-Tibet Province, and analyzes the reasons for the difference of minimum wage in different regions. The results show that Zhejiang Province has the largest influence factor of minimum wage, followed by economic development level and residents' living consumption level; Shanxi Province is residents' living consumption level; Guizhou Province is residents' living consumption level and spiritual and cultural level; Qinghai-Tibet Province accounts for the largest proportion of residents' living consumption level, followed by economic development level and spiritual and cultural consumption level. The influencing factors of minimum wage are also different in different regions, and the minimum wage standard should be reasonably formulated according to the local influencing factors.
{"title":"Research on Regional Differences of Influencing Factors of Minimum Wage ‐ ‐Based on Factor Analysis and LASSO Regression","authors":"Jinmin Zhang, Xufang Li, Dijun Fan","doi":"10.1109/ICCSMT54525.2021.00090","DOIUrl":"https://doi.org/10.1109/ICCSMT54525.2021.00090","url":null,"abstract":"The influencing factors of the minimum wage play an important role in the formulation of the minimum wage, and the minimum wage has a great impact on people's livelihood. Based on the data from 2001 to 2020, this paper uses factor analysis and LASSO regression to explore the influencing factors of minimum wage in Zhejiang Province, Shanxi Province, Guizhou Province and Qinghai-Tibet Province, and analyzes the reasons for the difference of minimum wage in different regions. The results show that Zhejiang Province has the largest influence factor of minimum wage, followed by economic development level and residents' living consumption level; Shanxi Province is residents' living consumption level; Guizhou Province is residents' living consumption level and spiritual and cultural level; Qinghai-Tibet Province accounts for the largest proportion of residents' living consumption level, followed by economic development level and spiritual and cultural consumption level. The influencing factors of minimum wage are also different in different regions, and the minimum wage standard should be reasonably formulated according to the local influencing factors.","PeriodicalId":304337,"journal":{"name":"2021 2nd International Conference on Computer Science and Management Technology (ICCSMT)","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125834237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：