Predicting Corporate Credit Ratings Using Content Analysis of Annual Reports – A Naïve Bayesian Network Approach

2017 ◽  
pp. 47-61 ◽  
Author(s):  
Petr Hajek ◽  
Vladimir Olej ◽  
Ondrej Prochazka
Keyword(s):  
Content Analysis ◽  
Bayesian Network ◽  
Credit Ratings ◽  
Annual Reports ◽  
Network Approach ◽  
Naive Bayesian ◽  
Corporate Credit ◽  
Naïve Bayesian

scholarly journals Detecting Bank False Account Based on Naive Bayesian Network

2020 ◽  
Vol 768 ◽  
pp. 072074
Author(s):  
Weiqing Wan ◽  
Qingyan Zeng ◽  
Zhicheng Wen
Keyword(s):  
Bayesian Network ◽  
Naive Bayesian ◽  
Naïve Bayesian

Domains of competence of the semi-naive Bayesian network classifiers

2014 ◽  
Vol 260 ◽  
pp. 120-148 ◽  
Author(s):  
M. Julia Flores ◽  
José A. Gámez ◽  
Ana M. Martínez
Keyword(s):  
Bayesian Network ◽  
Naive Bayesian ◽  
Bayesian Network Classifiers ◽  
Naïve Bayesian

A Novel Discriminative Naive Bayesian Network for Classification

2007 ◽  
pp. 1-12 ◽  
Author(s):  
Kaizhu Huang ◽  
Zenglin Xu ◽  
Irwin King ◽  
Michael R. Lyu ◽  
Zhangbing Zhou
Keyword(s):  
Bayesian Network ◽  
Discriminative Training ◽  
Support Vector ◽  
Naive Bayesian ◽  
Naïve Bayesian ◽  
Training Approach ◽  
Vector Machines ◽  
Series Of Experiments ◽  
Classification Tasks ◽  
Real World Datasets

Naive Bayesian network (NB) is a simple yet powerful Bayesian network. Even with a strong independency assumption among the features, it demonstrates competitive performance against other state-of-the-art classifiers, such as support vector machines (SVM). In this chapter, we propose a novel discriminative training approach originated from SVM for deriving the parameters of NB. This new model, called discriminative naive Bayesian network (DNB), combines both merits of discriminative methods (e.g., SVM) and Bayesian networks. We provide theoretic justifications, outline the algorithm, and perform a series of experiments on benchmark real-world datasets to demonstrate our model’s advantages. Its performance outperforms NB in classification tasks and outperforms SVM in handling missing information tasks.

Optimization of Dynamic Naive Bayesian Network Classifier with Continuous Attributes

2012 ◽  
Vol 11 (1) ◽  
pp. 676-679
Author(s):  
Rei-Jie Du ◽  
Shuang-Cheng Wang ◽  
Han-Xing Wang ◽  
Cui-Ping Leng
Keyword(s):  
Bayesian Network ◽  
Naive Bayesian ◽  
Naïve Bayesian ◽  
Bayesian Network Classifier

scholarly journals Universal Target Learning: An Efficient and Effective Technique for Semi-Naive Bayesian Learning

Entropy ◽  
2019 ◽  
Vol 21 (8) ◽  
pp. 729 ◽  
Author(s):  
SiQi Gao ◽  
Hua Lou ◽  
LiMin Wang ◽  
Yang Liu ◽  
Tiehu Fan
Keyword(s):  
Bayesian Network ◽  
Bayesian Learning ◽  
Training Data ◽  
Effective Technique ◽  
Bayesian Techniques ◽  
Naive Bayesian ◽  
Naïve Bayesian ◽  
Log Likelihood ◽  
Negative Effect ◽  
Bayesian Network Classifier

To mitigate the negative effect of classification bias caused by overfitting, semi-naive Bayesian techniques seek to mine the implicit dependency relationships in unlabeled testing instances. By redefining some criteria from information theory, Target Learning (TL) proposes to build for each unlabeled testing instance P the Bayesian Network Classifier BNC P , which is independent and complementary to BNC T learned from training data T . In this paper, we extend TL to Universal Target Learning (UTL) to identify redundant correlations between attribute values and maximize the bits encoded in the Bayesian network in terms of log likelihood. We take the k-dependence Bayesian classifier as an example to investigate the effect of UTL on BNC P and BNC T . Our extensive experimental results on 40 UCI datasets show that UTL can help BNC improve the generalization performance.

Sign in / Sign up

Export Citation Format

Share Document