检索结果-内蒙古大学图书馆

Machine learning models for early-stage investment decision making in startups

MANAGERIAL AND DECISION ECONOMICS 2024年第3期45卷 1259-1279页

作者： Shi, Yong Eremina, Ekaterina Long, Wen Univ Chinese Acad Sci Sch Econ & Management Beijing Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

This study demonstrates the efficacy of machine learning techniques for evidence-based evaluation of early-stage ventures. Leveraging real-world data on 24,965 startups across diverse sectors and countries sourced from Crunchbase, we develop predictive models using algorithms including random forest, XGBoost, and support vector machines. Rigorous training and testing on a 70-30 split of the data reveal that the algorithms can effectively classify startups as successful or not, achieving over 90% accuracy. Random forest emerges as the top performer, followed closely by XGBoost. This research demonstrates the immense potential of machine learning techniques in forecasting startup success to inform management practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The cluster D-trace loss for differential network analysis

引用

JOURNAL OF APPLIED STATISTICS 2024年第10期51卷 1843-1860页

作者： Yan, Han Lu, Shuhan Zhang, Sanguo 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 Pazhou Lab Guangzhou Peoples R China Univ Calif Los Angeles Dept Math Los Angeles CA USA

A growing literature suggests that gene expression can be greatly altered in disease conditions, and identifying those changes will improve the understanding of complex diseases such as cancers or diabetes. A prevailing direction in the analysis of gene expression studies the changes in gene pathways which include sets of related genes. Therefore, introducing structured exploration to differential analysis of gene expression networks may lead to meaningful discoveries. The topic of this paper is differential network analysis, which focuses on capturing the differences between two or more precision matrices. We discuss the connection between the thresholding method and the D-trace loss method on differential network analysis in the case that the precision matrices share the common connected components. Based on this connection, we further propose the cluster D-trace loss method which directly estimates the differential network and achieves model selection consistency. Simulation studies demonstrate its improved performance and computational efficiency. Finally, the usefulness of our proposed estimator is demonstrated by a real-data analysis on non-small cell lung cancer.

关键词： Gaussian graphical models high-dimensional setting precision matrices hierarchical clustering model selection consistency

来源：评论

学校读者我要写书评

暂无评论

A dynamic key node learning algorithm in evolving financial network: case study during the period of coronavirus 9th

A dynamic key node learning algorithm in evolving financial ...

引用

9th International Conference on Information Technology and Quantitative management, ITQM 2022

作者： Lu, Doudou Deng, Wei Xu, Yongyin Shi, Yong College of Big Data Statistics Guizhou University of Finance and Economics Guizhou550025 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Finding an influential set of nodes in the interconnected network, whose activities would maximally influence the development of overall network, is a fundamental topic in finance, biology, social science, epidemic control and other scenarios with respect to network science. In recent years, some works are proposed to find key nodes via network connectivity measures, these studies assume a static environment, and besides, key nodes are calculated through pairwise connectivity, the number of connected components and other measures from the perspective of graph theory. However, these studies leave out of consideration on the dynamic evolving environment and causal relationships in the network. In this paper, we introduce a key node learning algorithm in an evolving financial network. The intuition of the algorithm is to model the causality of financial entities over the time, and the metrics for cascading networks are proposed to grade the entities in the network. In the experiment, the worldwide financial activities before and during the period of coronavirus are analyzed. The proposed metrics can effectively capture the influential entities and quantitatively describe these influences on the whole financial system. © 2022 The Authors. Published by Elsevier B.V.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Fintech, technological innovation and regional economic growth: Theoretical modeling and empirical evidence

引用

CHINA ECONOMIC REVIEW 2025年 91卷

作者： Huang, Xirong Dong, Jichang Li, Xiuting Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China MOE Social Sci Lab Digital Econ Forecasts & Policy Hefei Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

This study aims to investigate the role of fintech in stimulating innovation and promoting regional economic growth. A Multi-Sector Endogenous Growth Model (MEGM) is constructed by incorporating fintech while internalizing technological progress and human capital accumulation within the framework of creative destruction. Based on this model, we theoretically analyze how fintech influences innovation and regional economic growth, followed by empirical testing using panel data from 246 prefecture-level cities in China during the period from 2012 to 2020. Furthermore, we contextualize these findings within China's fintech development landscape, trends in technological innovation, and patterns of regional economic growth. The results demonstrate that fintech exerts a significant incentive effect on regional innovation and effectively promotes economic growth. Heterogeneity analysis based on cities' endowments reveals that the impact of fintech is more pronounced in financially developed cities, those with high digital endowments, as well as in first- and second-tier cities. The analyses presented herein elucidate how fintech facilitates technology-driven regional economic growth in China, providing valuable insights for fostering innovation-driven development through fintech.

关键词： Fintech Technological innovation Economic growth Endogenous growth model Panel data analysis

来源：评论

学校读者我要写书评

暂无评论

Solving uncapacitated P-Median problem with reinforcement learning assisted by graph attention networks

引用

APPLIED INTELLIGENCE 2023年第2期53卷 2010-2025页

作者： Wang, Chenguang Han, Congying Guo, Tiande Ding, Man Univ Chinese Acad Sci Sch Math Sci 19A Yuquan Rd Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management 80 Zhonguancun East Rd Beijing 100190 Peoples R China

The P-Median Problem is one of the basic cases of facility location problems and has been studied for many years. Most methods of solving it are based on classical heuristics or meta-heuristic and they don't perform well on large-scale problems according to time cost. In this paper, we propose the first reinforcement learning-based method which uses Multi-Talking-Heads Graph Attention Networks to learn representations and design a learnable attention mechanism to solve the uncapacitated P-Median Problem. We train the model using REINFORCE algorithm and show that it has good performance on uncapacitated P-Median Problem according to solution quality and time consumption. We also apply our model to the realistic dataset and empirically figure out that the difference between data distributions is one of the most important factors to influence the final performances.

关键词： P-median problem Graph neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

End-to-End Multitask Learning With Vision Transformer

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第7期35卷 9579-9590页

作者： Tian, Yingjie Bai, Kunlong Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100190 Peoples R China

Multitask learning (MTL) is a challenging puzzle, particularly in the realm of computer vision (CV). Setting up vanilla deep MTL requires either hard or soft parameter sharing schemes that employ greedy search to find the optimal network designs. Despite its widespread application, the performance of MTL models is vulnerable to under-constrained parameters. In this article, we draw on the recent success of vision transformer (ViT) to propose a multitask representation learning method called multitask ViT (MTViT), which proposes a multiple branch transformer to sequentially process the image patches (i.e., tokens in transformer) that are associated with various tasks. Through the proposed cross-task attention (CA) module, a task token from each task branch is regarded as a query for exchanging information with other task branches. In contrast to prior models, our proposed method extracts intrinsic features using the built-in self-attention mechanism of the ViT and requires just linear time on memory and computation complexity, rather than quadratic time. Comprehensive experiments are carried out on two benchmark datasets, including NYU-Depth V2 (NYUDv2) and CityScapes, after which it is found that our proposed MTViT outperforms or is on par with existing convolutional neural network (CNN)-based MTL methods. In addition, we apply our method to a synthetic dataset in which task relatedness is controlled. Surprisingly, experimental results reveal that the MTViT exhibits excellent performance when tasks are less related.

关键词： Task analysis Transformers Neural networks Visualization Biological system modeling Benchmark testing Correlation Deep neural network algorithms machine learning applications multitask learning (MTL)

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function

引用

IEEE TRANSACTIONS ON CYBERNETICS 2023年第2期53卷 1051-1062页

作者： Li, Kai Wang, Bo Tian, Yingjie Qi, Zhiquan Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Univ Int Business & Econ Sch Informat Technol & Management Beijing 100029 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance. Fortunately, modification of loss function appears to solve this puzzle once and for all. In this article, we propose a pixel-based adaptive weighted cross-entropy (WCE) loss in conjunction with Jaccard distance to facilitate high-quality pixel-level road crack detection. Our work profoundly demonstrates the influence of loss functions on detection outcomes and sheds light on the sophisticated consecutive improvements in the realm of crack detection. Specifically, to verify the effectiveness of the proposed loss, we conduct extensive experiments on four public databases, that is, CrackForest, AigleRN, Crack360, and BJN260. Compared to the vanilla WCE, the proposed loss significantly speeds up the training process while retaining the performance.

关键词： Roads Training Costs Image edge detection Training data Sampling methods Adaptation models Crack detection Jaccard distance U-Net weighted cross-entropy (WCE)

来源：评论

学校读者我要写书评

暂无评论

On inexact stochastic splitting methods for a class of nonconvex composite optimization problems with relative error

引用

OPTIMIZATION METHODS & SOFTWARE 2023年第1期38卷 1-33页

作者： Hu, Jia Han, Congying Guo, Tiande Zhao, Tong Univ Chinese Acad Sci Sch Math Sci 19A Yuquan Rd Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management 80 Zhongguancun East Rd Beijing 100190 Peoples R China

We consider minimizing a class of nonconvex composite stochastic optimization problems, and deterministic optimization problems whose objective function consists of an expectation function (or an average of finitely many smooth functions) and a weakly convex but potentially nonsmooth function. And in this paper, we focus on the theoretical properties of two types of stochastic splitting methods for solving these nonconvex optimization problems: stochastic alternating direction method of multipliers and stochastic proximal gradient descent. In particular, several inexact versions of these two types of splitting methods are studied. At each iteration, the proposed schemes inexactly solve their subproblems by using relative error criteria instead of exogenous and diminishing error rules, which allows our approaches to handle some complex regularized problems in statistics and machine learning. Under mild conditions, we obtain the convergence of the schemes and their computational complexity related to the evaluations on the component gradient of the smooth function, and find that some conclusions of their exact counterparts can be recovered.

关键词： Nonsmooth nonconvex optimization stochastic approximation relative error alternating direction method of multipliers proximal gradient descent variance reduction

来源：评论

学校读者我要写书评

暂无评论

Credit risk assessment method driven by asymmetric loss function

引用

APPLIED SOFT COMPUTING 2024年 167卷

作者： Zhao, Xiaoxi Tian, Yingjie Hangzhou Dianzi Univ Sch Management Hangzhou 310018 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China UCAS MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China

Credit risk assessment is significantly hindered by the problem of class imbalance, and cost-sensitive methods represent an effective strategy to address this issue. However, most algorithms tend to approach the imbalance from a class perspective, overlooking the finer details at the sample level. Moreover, such methods are susceptible to interference from noise and outliers. In response to these challenges, this paper proposes an asymmetric cost-sensitive support vector machine (QTSVM) that combines the quadratic type squared error loss function (QTSELF) with support vector machine (SVM). It not only leverages the asymmetry of the loss function by applying varying penalties based on classification errors but also employs different processing measures for samples from different classes. Additionally, it enhances model robustness by imposing a tiny penalty on noise or outliers. The adaptive moment estimation (Adam) algorithm is employed to optimize QTSVM. Extensive experiments and statistical tests profoundly demonstrate the superior performance of QTSVM.

关键词： Class imbalance Credit risk assessment Cost sensitive Support vector machine Loss function

来源：评论

学校读者我要写书评

暂无评论

TGformer: A Graph Transformer Framework for knowledge Graph Embedding

引用

IEEE TRANSACTIONS ON knowledge AND data ENGINEERING 2025年第1期37卷 526-541页

作者： Shi, Fobo Li, Duantengchuan Wang, Xiaoguang Li, Bing Wu, Xindong Wuhan Univ Sch Informat Management Wuhan 430072 Peoples R China Wuhan Univ Intelligent Comp Lab Cultural Heritage Wuhan 430072 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ China Hefei 230009 Peoples R China

knowledge graph embedding is efficient method for reasoning over known facts and inferring missing links. Existing methods are mainly triplet-based or graph-based. Triplet-based approaches learn the embedding of missing entities by a single triple only. They ignore the fact that the knowledge graph is essentially a graph structure. Graph-based methods consider graph structure information but ignore the contextual information of nodes in the knowledge graph, making them unable to discern valuable entity (relation) information. In response to the above limitations, we propose a general graph transformer framework for knowledge graph embedding (TGformer). It is the first to use a graph transformer to build knowledge embeddings with triplet-level and graph-level structural features in the static and temporal knowledge graph. Specifically, a context-level subgraph is constructed for each predicted triplet, which models the relation between triplets with the same entity. Afterward, we design a knowledge graph transformer network (KGTN) to fully explore multi-structural features in knowledge graphs, including triplet-level and graph-level, boosting the model to understand entities (relations) in different contexts. Finally, semantic matching is adopted to select the entity with the highest score. Experimental results on several public knowledge graph datasets show that our method can achieve state-of-the-art performance in link prediction.

关键词： knowledge graph graph transformer link prediction knowledge graph graph transformer link prediction

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：