Pub Date : 2021-04-01DOI: 10.1109/CBFD52659.2021.00059
Wang Jun-di, Zhu Ya-Ling, Wang Juan
Identifying important nodes in complex networks in a fast and effective manner is one of the useful ways to control the network communication process. Degree centrality and K-Shell decomposition are combined to integrate the global and local characteristics of the nodes, without depending on other parameters in the calculation. This effectively improves the shortcomings of poor discrimination by K-Shell decomposition and increases the resolution of node identification.
{"title":"An improved K-Shell-Based Ranking of Node Importance","authors":"Wang Jun-di, Zhu Ya-Ling, Wang Juan","doi":"10.1109/CBFD52659.2021.00059","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00059","url":null,"abstract":"Identifying important nodes in complex networks in a fast and effective manner is one of the useful ways to control the network communication process. Degree centrality and K-Shell decomposition are combined to integrate the global and local characteristics of the nodes, without depending on other parameters in the calculation. This effectively improves the shortcomings of poor discrimination by K-Shell decomposition and increases the resolution of node identification.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127163679","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00010
Zhang Huabing, Ye Sisi, C. Xiaoming, Lin Zhida
The traditional network traffic anomaly detection method is based on the principle of feature extraction and matching for a large amount of abnormal traffic data to achieve traffic anomaly detection. Due to the fast changing speed of mobile networks, it is difficult to ensure the real-time and accuracy of the detection method simply by extracting traffic features. To address the above problems, the study considers the real-time detection method of mobile network traffic anomaly for user behavior security monitoring. User behavior data is captured based on the network usage data of users provided by mobile network providers. Protocol parsing and application identify user data packets and extract user behavior features. A Bayesian classifier is constructed and a HAST-NAD model is used to achieve real-time detection of network traffic anomalies. Simulation experimental results show that the highest detection time of the detection method is only 104s, and the detection accuracy of the method is better than the traditional detection method, and the detection effect is better.
{"title":"Real-time detection method for mobile network traffic anomalies considering user behavior security monitoring","authors":"Zhang Huabing, Ye Sisi, C. Xiaoming, Lin Zhida","doi":"10.1109/CBFD52659.2021.00010","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00010","url":null,"abstract":"The traditional network traffic anomaly detection method is based on the principle of feature extraction and matching for a large amount of abnormal traffic data to achieve traffic anomaly detection. Due to the fast changing speed of mobile networks, it is difficult to ensure the real-time and accuracy of the detection method simply by extracting traffic features. To address the above problems, the study considers the real-time detection method of mobile network traffic anomaly for user behavior security monitoring. User behavior data is captured based on the network usage data of users provided by mobile network providers. Protocol parsing and application identify user data packets and extract user behavior features. A Bayesian classifier is constructed and a HAST-NAD model is used to achieve real-time detection of network traffic anomalies. Simulation experimental results show that the highest detection time of the detection method is only 104s, and the detection accuracy of the method is better than the traditional detection method, and the detection effect is better.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132026253","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00082
Lin Li
With the continuous improvement of China's macropolicies in the field of blockchain and the increasing industrial investment, the research and application of blockchain technology are changing with each passing day and develop vigorously, and the integrated application of blockchain technology plays an important role in the new technological innovation and industrial reform. The characteristics of blockchain, such as decentralization, tamper proof and traceability, enable it to play a vital role in many areas, such as finance, intelligent manufacturing, Internet of Things, supplychain management, digital asset trading, social governance and the people's livelihood services. Accelerating the innovative development of blockchain technology and industry is conducive to expanding the application fields and development prospects of blockchain technology, helping China to achieve a leading edge in global technological competition and promoting the high-quality development of China's economy and society.
{"title":"Accelerate the innovative development of blockchain technology and industry","authors":"Lin Li","doi":"10.1109/CBFD52659.2021.00082","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00082","url":null,"abstract":"With the continuous improvement of China's macropolicies in the field of blockchain and the increasing industrial investment, the research and application of blockchain technology are changing with each passing day and develop vigorously, and the integrated application of blockchain technology plays an important role in the new technological innovation and industrial reform. The characteristics of blockchain, such as decentralization, tamper proof and traceability, enable it to play a vital role in many areas, such as finance, intelligent manufacturing, Internet of Things, supplychain management, digital asset trading, social governance and the people's livelihood services. Accelerating the innovative development of blockchain technology and industry is conducive to expanding the application fields and development prospects of blockchain technology, helping China to achieve a leading edge in global technological competition and promoting the high-quality development of China's economy and society.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133526142","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00031
Yiwei Hong, Su Zhou, Dejing Niu
This article will be based on the data of Douban and Maoyan platforms, using python to analyze the box office, investment amount, movie types, the popularity of actors and directors and ratings of movies to measure the market value of movies. According to the relationship reflected in the data, we found that the most important driving force influencing the market value of movies is famous actors, followed by famous directors. In addition, the amount of investment is also an important factor for movies, but it is not a necessary factor. In the end, we came to conclusion that in order to improve the market value of movies, we must first work hard on the content. In addition, the participation of famous actors and famous directors, and the increase in investment amount will also greatly increase the market value of the film.
{"title":"Multi-directional market value analysis of films : Visual data processing based on Python","authors":"Yiwei Hong, Su Zhou, Dejing Niu","doi":"10.1109/CBFD52659.2021.00031","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00031","url":null,"abstract":"This article will be based on the data of Douban and Maoyan platforms, using python to analyze the box office, investment amount, movie types, the popularity of actors and directors and ratings of movies to measure the market value of movies. According to the relationship reflected in the data, we found that the most important driving force influencing the market value of movies is famous actors, followed by famous directors. In addition, the amount of investment is also an important factor for movies, but it is not a necessary factor. In the end, we came to conclusion that in order to improve the market value of movies, we must first work hard on the content. In addition, the participation of famous actors and famous directors, and the increase in investment amount will also greatly increase the market value of the film.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132903497","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00008
Yang Kunqiao, Jiang Jiandong
In order to accurately predict the short-term load, a combination forecasting model based on extreme learning machine is proposed. First, variational modal technology is used to decompose the original load sequence, and the appropriate number of modal components is obtained; secondly, according to the different performance characteristics of each modal, the time series and extreme learning machine model is used for prediction, and the improved bat algorithm is used to optimize the selection of parameters in the extreme learning machine; finally, the output value of the model built by each sub-sequence is reconstructed to obtain the final prediction result. Through the measured data, the effectiveness and accuracy of the combined forecasting model proposed in this paper are verified in load forecasting.
{"title":"Short-term load forecasting based on ELM combined model","authors":"Yang Kunqiao, Jiang Jiandong","doi":"10.1109/CBFD52659.2021.00008","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00008","url":null,"abstract":"In order to accurately predict the short-term load, a combination forecasting model based on extreme learning machine is proposed. First, variational modal technology is used to decompose the original load sequence, and the appropriate number of modal components is obtained; secondly, according to the different performance characteristics of each modal, the time series and extreme learning machine model is used for prediction, and the improved bat algorithm is used to optimize the selection of parameters in the extreme learning machine; finally, the output value of the model built by each sub-sequence is reconstructed to obtain the final prediction result. Through the measured data, the effectiveness and accuracy of the combined forecasting model proposed in this paper are verified in load forecasting.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129489506","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00026
Chen Zhang, Hong Li, Guangde Xu, Xuhui Zhu
How to prevent the loss of bank customers, especially the loss of high-quality customers, is a great concern of banks, for which an accurate churn prediction model is of great importance. The accuracy of the integrated classifier is better than that of a single classifier. Random forest is a kind of ensemble learning. Traditional random forest uses all decision trees for voting. Some poor decision trees will reduce the overall performance of random forests. To improve the performance of traditional random forest, the random forest based on complementarity measure is proposed. The decision trees in the forest are pruned using complementarity measure. We use the proposed method to predict bank customer churn. Firstly, affinity propagation clustering (AP clustering) algorithm is used for attribute selection. Then the improved random forest method is used to establish an early warning model of customer churn. Compared with the general churn prediction model, this model has higher accuracy.
{"title":"Customer churn model based on complementarity measure and random forest","authors":"Chen Zhang, Hong Li, Guangde Xu, Xuhui Zhu","doi":"10.1109/CBFD52659.2021.00026","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00026","url":null,"abstract":"How to prevent the loss of bank customers, especially the loss of high-quality customers, is a great concern of banks, for which an accurate churn prediction model is of great importance. The accuracy of the integrated classifier is better than that of a single classifier. Random forest is a kind of ensemble learning. Traditional random forest uses all decision trees for voting. Some poor decision trees will reduce the overall performance of random forests. To improve the performance of traditional random forest, the random forest based on complementarity measure is proposed. The decision trees in the forest are pruned using complementarity measure. We use the proposed method to predict bank customer churn. Firstly, affinity propagation clustering (AP clustering) algorithm is used for attribute selection. Then the improved random forest method is used to establish an early warning model of customer churn. Compared with the general churn prediction model, this model has higher accuracy.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133125249","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00086
Lei Zhou, Xiao Ya Zhong, J. Liu, M. Xia
The integration of blockchain and supply chain provides new possibilities for solving the financing difficulties of small and micro enterprises (SMEs). This paper constructs dynamic evolutionary game models between financial institutions and SMEs as well as core firms and SMEs. Furthermore, the following conclusions were drawn by using MATLAB software for numerical simulation based on models combined with the example. Docking with blockchain platform is the dominant strategy of financial institutions. Blockchain can help SMEs make trustworthy decisions by promoting credit split circulation, improving financing efficiency, increasing default cost and reducing financing rate. In addition, through "network cooperation and credit incentive", "joint punishment for breach of trust" and "reasonable revenue sharing", the game equilibrium evolves toward the ideal state that financial institutions dare to lend, core firms and SMEs are "Double Trustworthy". Thus, the financing of SMEs is empowered by blockchain. Finally, according to the results of game analysis, suggestions that blockchain should be used to develop digital supply chain to meet the financing needs of SMEs are proposed.
{"title":"Game Analysis of \"Blockchain+Supply Chain Finance\" Mode in Empowering Small and Micro Enterprises’ Financing","authors":"Lei Zhou, Xiao Ya Zhong, J. Liu, M. Xia","doi":"10.1109/CBFD52659.2021.00086","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00086","url":null,"abstract":"The integration of blockchain and supply chain provides new possibilities for solving the financing difficulties of small and micro enterprises (SMEs). This paper constructs dynamic evolutionary game models between financial institutions and SMEs as well as core firms and SMEs. Furthermore, the following conclusions were drawn by using MATLAB software for numerical simulation based on models combined with the example. Docking with blockchain platform is the dominant strategy of financial institutions. Blockchain can help SMEs make trustworthy decisions by promoting credit split circulation, improving financing efficiency, increasing default cost and reducing financing rate. In addition, through \"network cooperation and credit incentive\", \"joint punishment for breach of trust\" and \"reasonable revenue sharing\", the game equilibrium evolves toward the ideal state that financial institutions dare to lend, core firms and SMEs are \"Double Trustworthy\". Thus, the financing of SMEs is empowered by blockchain. Finally, according to the results of game analysis, suggestions that blockchain should be used to develop digital supply chain to meet the financing needs of SMEs are proposed.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127635853","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00047
Xingxiang Qi
This paper uses ARIMA model and neural network model to forecast China's GDP data from 1978 to 2020. The prediction results of the two models for time series data are compared. The results of GDP forecasting show that neural networks is better at predicting nonlinear data.
{"title":"Research on Time Series Data Forecasting Models Based on ARIMA and Neural Networks : Empirical Analysis Based on China's GDP Data from 1978 to 2020","authors":"Xingxiang Qi","doi":"10.1109/CBFD52659.2021.00047","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00047","url":null,"abstract":"This paper uses ARIMA model and neural network model to forecast China's GDP data from 1978 to 2020. The prediction results of the two models for time series data are compared. The results of GDP forecasting show that neural networks is better at predicting nonlinear data.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123649890","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00058
Yinuo Zhang, Zhongfu Zhou
Iron ore futures price forecasting has been studied widely in recent years, and a wild range of variables that may have impacts on the price volatility was considered. However, the impacts of the day-of-the-week effect on the volatility of iron ore futures' price are still left undiscussed. Based on heterogeneous auto-regressive (HAR) theory, this paper establishes a new type of HAR model by considering the day-of-the-week effect in forecasting volatility. The empirical results indicate that, compared to the original HAR model, the new model's accuracy improves in the short terms. It also shows that the day-of-the-week effect has a significantly negative influence on iron ore futures' price volatility, especially on Monday and Tuesday. The result of this paper provides a new perspective in iron ore futures volatility forecasting.
{"title":"Forecast on iron ore futures price linked with day-of-the-week effect","authors":"Yinuo Zhang, Zhongfu Zhou","doi":"10.1109/CBFD52659.2021.00058","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00058","url":null,"abstract":"Iron ore futures price forecasting has been studied widely in recent years, and a wild range of variables that may have impacts on the price volatility was considered. However, the impacts of the day-of-the-week effect on the volatility of iron ore futures' price are still left undiscussed. Based on heterogeneous auto-regressive (HAR) theory, this paper establishes a new type of HAR model by considering the day-of-the-week effect in forecasting volatility. The empirical results indicate that, compared to the original HAR model, the new model's accuracy improves in the short terms. It also shows that the day-of-the-week effect has a significantly negative influence on iron ore futures' price volatility, especially on Monday and Tuesday. The result of this paper provides a new perspective in iron ore futures volatility forecasting.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124043649","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 : 2021-04-01DOI: 10.1109/CBFD52659.2021.00064
Qinyi Wang
Recently there is a growing amount of Internet data available. And investors of the stock market have an increasing demand for using these valuable Internet data to guide their investment decision. We crawled the attention of some hot-words and plate words on different social media through python and regressed them with the stock price in the same period. It was divided into two parts: hot words and stock price, plate words, and stock price. Combined with the Granger causality test framework, it was found that the popularity of keywords had a certain impact on the relevant stock price. Still, most of its impact coincided with the impact of the market on the stock price. This also showed that the market is efficient. The influence of the attention of hot words on the market trend depends on the nature of the words. The wider the audience, the greater the impact on the market. We use the popularity of keywords to predict the stock returns by a statistical data mining model. We think that this may better predict the trend of the A-share market and has more timeliness. Simultaneously, it can more comprehensively reflect the actual operation of China’s A-share market from the perspective of investors.
{"title":"Predicting Chinese Stock Market with Internet Key Word Hotness by Statistical Time Series Regression Analysis","authors":"Qinyi Wang","doi":"10.1109/CBFD52659.2021.00064","DOIUrl":"https://doi.org/10.1109/CBFD52659.2021.00064","url":null,"abstract":"Recently there is a growing amount of Internet data available. And investors of the stock market have an increasing demand for using these valuable Internet data to guide their investment decision. We crawled the attention of some hot-words and plate words on different social media through python and regressed them with the stock price in the same period. It was divided into two parts: hot words and stock price, plate words, and stock price. Combined with the Granger causality test framework, it was found that the popularity of keywords had a certain impact on the relevant stock price. Still, most of its impact coincided with the impact of the market on the stock price. This also showed that the market is efficient. The influence of the attention of hot words on the market trend depends on the nature of the words. The wider the audience, the greater the impact on the market. We use the popularity of keywords to predict the stock returns by a statistical data mining model. We think that this may better predict the trend of the A-share market and has more timeliness. Simultaneously, it can more comprehensively reflect the actual operation of China’s A-share market from the perspective of investors.","PeriodicalId":230625,"journal":{"name":"2021 International Conference on Computer, Blockchain and Financial Development (CBFD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122663966","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：