检索结果-内蒙古大学图书馆

Can investor sentiment be used to predict the stock price? Dynamic analysis based on China stock market

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2017年 469卷 390-396页

作者： Guo, Kun Sun, Yi Qian, Xin Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Northeastern Univ Sch Business Adm Shenyang Peoples R China

With the development of the social network, the interaction between investors in stock market became more fast and convenient. Thus, investor sentiment which can influence their investment decisions may be quickly spread and magnified through the network, and to a certain extent the stock market can be affected. This paper collected the user comments data from a popular professional social networking site of China stock market called Xueqiu, then the investor sentiment data can be obtained through semantic analysis. The dynamic analysis on relationship between investor sentiment and stock market is proposed based on Thermal Optimal Path (TOP) method. The results show that the sentiment data was not always leading over stock market price, and it can be used to predict the stock price;only when the stock has high investor attention. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Investor sentiment Thermal optimal path Stock market Dynamic analysis

来源：评论

学校读者我要写书评

暂无评论

Online Robust Lagrangian Support Vector Machine against Adversarial Attack

引用

Procedia Computer Science 2018年 139卷 173-181页

作者： Yue Ma Yiwei He Yingjie Tian School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100049 China Key Laboratory of Big Data Mining and Knowledge management Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China

In adversarial environment such as intrusion detection and spam filtering, the adversary-intruder or spam advertiser may attempt to produce contaminate training instance and manipulate the learning of classifier. In order to keep good classification performance, many robuster learning methods have been proposed to deal with the adversarial attack. Support Vector Machines(SVMs) is a kind of successful approach in the adversarial classification tasks and the investigation of robust SVMs is very popular. However, in many real application, the data including stain instance is coming dynamically. Batch learning which needs retraining when encountering new samples, will consume more computing resources. In this paper, we propose a robust Lagrangian support vector machine (RLSVM) with modified kernel matrix and explore the online learning algorithm on it. The experimental results show the robustness of RLSVM against label noise produced by adversaries under the online adversarial environment.

关键词： adversarial attack poison attack label noise online learning Lagrangian SVM

来源：评论

学校读者我要写书评

暂无评论

A Margin-based MLE for Crowdsourced Partial Ranking 18

A Margin-based MLE for Crowdsourced Partial Ranking

引用

26th ACM Multimedia Conference (MM)

作者： Xu, Qianqian Xiong, Jiechao Sun, Xinwei Yang, Zhiyong Cao, Xiaochun Huang, Qingming Yao, Yuan Chinese Acad Sci Inst Comput Tech Key Lab Intell Info Proc Beijing 100190 Peoples R China Tencent AI Lab Shenzhen 518057 Peoples R China Peking Univ Sch Math Sci Beijing 100871 Peoples R China DeepWise AI Lab Beijing 100085 Peoples R China Chinese Acad Sci Inst Info Engin State Key Lab Info Secur SKLOIS Beijing 100093 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Hong Kong Univ Sci & Technol Dept Math Hong Kong Peoples R China

ISBN: (纸本)9781450356657

A preference order or ranking aggregated from pairwise comparison data is commonly understood as a strict total order. However, in real-world scenarios, some items are intrinsically ambiguous in comparisons, which may very well be an inherent uncertainty of the data. In this case, the conventional total order ranking can not capture such uncertainty with mere global ranking or utility scores. In this paper, we are specifically interested in the recent surge in crowdsourcing applications to predict partial but more accurate (i.e., making less incorrect statements) orders rather than complete ones. To do so, we propose a novel framework to learn some probabilistic models of partial orders as a margin-based Maximum Likelihood Estimate (MLE) method. We prove that the induced MLE is a joint convex optimization problem with respect to all the parameters, including the global ranking scores and margin parameter. Moreover, three kinds of generalized linear models are studied, including the basic uniform model, Bradley-Terry model, and Thurstone-Mosteller model, equipped with some theoretical analysis on FDR and Power control for the proposed methods. The validity of these models are supported by experiments with both simulated and real-world datasets, which shows that the proposed models exhibit improvements compared with traditional state-of-the-art algorithms.

关键词： Partial Ranking Pairwise Comparison Crowdsourcing Margin-based MLE

来源：评论

学校读者我要写书评

暂无评论

An Efficient Algorithm for Judicious Partition of Hypergraphs 11th

An Efficient Algorithm for Judicious Partition of Hypergraph...

引用

11th Annual International Conference on Combinatorial Optimization and Applications (COCOA)

作者： Tan, Tunzi Gui, Jihong Wang, Sainan Gao, Suixiang Yang, Wenguo Univ Chinease Acad Sci Sch Math Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

ISBN: (纸本)9783319711478;9783319711461

Judicious partition of hypergraphs H=(V, H) is to optimize several quantities simultaneously, and the goal of this paper is to partition the vertex set V into K parts: {V1, V2,, VK} so as to minimize the max{L(Vi), L(V2),, L(VK)}, where L(V3) is the number of hyperedges incident to the part V3 (H). The bounds for the objective function are given and the relationship between the maximum hyperdegree and the objective value is analyzed. Before giving an efficient algorithm for the judicious partition of hypergraphs, a sub -problem is obtained, which is proved to be an unweighted set cover problem, apart from a tiny difference. A greedy algorithm is applied to solve the sub -problem. Last but not least, the judicious partition of hypergraphs is successfully divided into a series of sub -problems and an efficient algorithm is developed for the original problem.

关键词： Hypergraph Judicious partition Approximation algorithm Minimum set cover

来源：评论

学校读者我要写书评

暂无评论

CNN-MR for No Reference Video Quality Assessment 4

CNN-MR for No Reference Video Quality Assessment

引用

4th International Conference on Information Science and Control Engineering (ICISCE)

作者： Wang, Chunfeng Su, Li Huang, Qingming Univ Chinese Acad Sci Sch Comp & Control Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

ISBN: (纸本)9781538630136

In this paper, we propose a no-reference video quality assessment (VQA) method based on Convolutional Neural Network (CNN) and Multi-Regression (CNN-MR). It is universal for non-specific types of distortion. First, we innovatively introduce the 2D convolutional neural network into VQA model to learn the spatial quality features at frame level. Second, the motion information is extracted as temporal quality features at sequence level. Finally, a multi-regression model is proposed to comprehensively measure video quality and the final quality is selected out from them according to human's psychological perception. The proposed CNN-MR method is tested on the famous LIVE database with numerous kinds of distortions. Compared with other state-of-the-art no reference VQA methods, the proposed method runs much faster while keeping the similar performance. As a no-reference VQA method, it is even comparable with most of the state-of-the-art full-reference VQA methods.

关键词： no-reference video quality assessment convolutional neural network multi-regression

来源：评论

学校读者我要写书评

暂无评论

Daily Ship Traffic Volume Statistics and Prediction Based on Automatic Identification System data 9

Daily Ship Traffic Volume Statistics and Prediction Based on...

引用

9th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)

作者： Wang, Sainan Wang, Si Gao, Suixiang Yang, Wenguo Univ Chinese Acad Sci Sch Math Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

ISBN: (纸本)9781538630228

Daily ship traffic volume statistics and prediction are of great significance to shipping market. Reliable prediction of daily ship traffic volume can instruct shipping company to make sound judgment and decision for operational management. Because of the mobility of ships, it may be difficult to obtain the ship traffic volume automatically and frequently. This paper defines four types' daily ship traffic volume for a port and proposes autonomous statistic methods for counting daily ship traffic volume at port only based on Automatic Identification System (AIS) data. Take Shanghai port as instance, we count the daily ship traffic volume by using the proposed statistic methods for three common types of ship: cargo ship, passenger ship, and tanker ship. For ship traffic volume prediction, we apply a hybrid methodology that combines both Auto-Regressive and Moving Average (ARMA) and Artificial Neural Network (ANN) models to cargo ship and tanker ship, and show the comparison of ARMA, ANN and the hybrid methodology. Empirical results indicate that the hybrid methodology is efficient and superior for ship traffic volume prediction. But for passenger ship traffic volume, since the correlation coefficient plot shows feeble correlation in it, we just analyze some statistical characters for it.

关键词： Automatic Identification System (AIS) Daily ship traffic volume statistics and prediction Auto-Regressive and Moving Average (ARMA) Artificial Neural Network (ANN) Hybrid methodology

来源：评论

学校读者我要写书评

暂无评论

The performance of one belt and one road exchange rate: Based on improved singular spectrum analysis

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2017年 483卷 299-308页

作者： Lai, Lin Guo, Kun China Univ Polit Sci & Law Business Sch Beijing Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

"One Belt and One Road" strategy in China is on push of foreign trade openness at northwest, southwest and northeast, absorption of the excess capacity and new support for economic increase. However, the fluctuation in RMB exchange rate with the countries along the road is unstable so related Chinese enterprises will face high risk of exchange rate. Precise explanation or prediction for exchange rate has been the challengeable hop point in the international finance. This paper decomposed the One Belt One Road Exchange Rate Index (OBORR) and the RMB Effective Exchange Rate Index (CNYX) into trend term, market fluctuation term and noise term using improved singular spectrum analysis (SSA). It turns out that the increasing velocity of OBORR is greater than that of CNYX in the long term, and there is dynamic lead-lag structure in the medium term. In the short term, the fluctuation range and frequency of OBORR are greater than those of CNYX, which means there will be more exchange rate risks in One Belt and One Road countries. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Singular spectrum analysis Increment for singular entropy One belt one road Exchange rate Thermal optimal path

来源：评论

学校读者我要写书评

暂无评论

Development and application of an energy use and CO₂ emissions reduction evaluation model for China's online car hailing services

引用

ENERGY 2018年 154卷 298-307页

作者： Wu, Tian Shen, Qu Xu, Ming Peng, Tianduo Ou, Xunmin Chinese Acad Sci Acad Math & Syst Sci Beijing Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Univ Michigan Sch Environm & Sustainabil Ann Arbor MI 48109 USA Univ Michigan Dept Civil & Environm Engn Ann Arbor MI 48109 USA Tongji Univ Sustainable Dev & New Type Urbanizat Think Tank Shanghai Peoples R China Tsinghua Univ Inst Energy Environm & Econ Beijing Peoples R China Tsinghua Univ China Automot Energy Res Ctr Beijing Peoples R China

Emerging online car hailing services have caused many unintended consequences in urban centers such as more congested traffic and increased vehicle travels. Those unintended consequences have significant impacts on urban sustainability due to the increased fuel use and carbon dioxide (CO2) emissions. An evaluation model of online car hailing services was established to evaluate impact on energy use and CO2 in China. We found online car hailing services have taken over not only private vehicle travels but also travels fulfilled by other modes such as mass public transit, walking, and bicycling. Empirical case analysis combined with real data shows the operating mechanism, quantitative research method and different future scenario analysis results of the model we developed. Our findings suggest that policies should be developed to prevent online car hailing from attracting too many public transit riders and to improve the efficiency of private vehicle travels. As online car hailing is emerging in many cities around the world, lessons learned from China will be useful to inform the development of policies to avoid unintended consequences. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Online car hailing services Comprehensive evaluation model Energy use CO2 emissions Transport policy China

来源：评论

学校读者我要写书评

暂无评论

Finding Patterns of Stock Returns Based on Sequence Alignment

引用

Procedia Computer Science 2018年 139卷 256-262页

作者： Yong Shi Ye-ran Tang Wen Long School of Economics & Management University of Chinese Academy of Sciences Beijing 100190 P.R. China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 P.R. China Key Laboratory of Big Data Mining & Knowledge Management Chinese Academy of Sciences Beijing 100190 P.R. China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 USA

In this paper, we propose the method based on sequence alignment to find patterns of stock returns. We use 5 minutes high frequency data of CSI 300 index to test this method, and find we can predict the sharply rise or drop for the stock returns according to patterns of the sample symbol sequence. The empirical analysis suggests it is possible to find and predict patterns in stock returns based on the method of sequence alignment.

关键词： finding patterns sequence alignment stock returns

来源：评论

学校读者我要写书评

暂无评论

An exact algorithm for Min-Max hyperstructure equipartition with a connected constraint

引用

COMPUTERS & OPERATIONS RESEARCH 2017年 87卷 183-193页

作者： Tan, Tunzi Gao, Suixiang Mesa, Juan A. Univ Chinese Acad Sci Sch Math Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Univ Seville Dpto Matemat Aplicada 2 Escuela Tecn Super Ingn Seville Spain

Hyperstructure is a topological concept that shares characteristics with both graphs and hypergraphs. The Min-Max hyperstructure equipartition with a connected constraint problem consists in partitioning a hyperstructure into K equal-sized connected parts that minimizes the maximum load in each part (the number of hyperedges assigned to each part). This problem, proved to be NP-hard, is an integer nonlinear programming problem. The linearized version of this problem has been introduced. Shrink and Cut algorithm is designed to simplify original complex hyperstructure without changing the optimal solution of the Min-Max hyperstructure equipartition with a connected constraint problem. By the use of this algorithm, Min-Max hyper-tree equipartition with a connected constraint can be solved in polynomial time. An exact algorithm: Min-Max hyperstructure partitioning algorithm, based on a Shrink and Cut algorithm and algorithm S for finding all the spanning trees, is designed to solve ordinary cases, which shows well on experimental results. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Hyperstructure equipartition NP-Hard Minimax programming Connected constraint Balanced constraint Rapid transit network

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：