Construction and Application of the Financial Early-Warning Model Based on the BP Neural Network

Jiang, Weiwei; Wu, Xuefeng; Wang, Xi

doi:10.1155/2022/5108677

Cited by 6 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The optimization of the BPNN model is the adjustment of specific parameters, such as adding hidden layers, adding single-layer neurons, increasing the maximum number of iterations, selecting different weight optimizers and activation functions, etc. In the early warning research on financial risks, Wang Ting et al constructed a variety of BPNN models to compare the results, and found that when the number of hidden layers increased from 1 to 3, the model learning accuracy and learning rate were more obvious improvement [12]. However, as the complexity of the hidden layer network increases, the learning efficiency of a single neuron node decreases, the network convergence speed decreases, and the error increases.…”

Section: Plos Onementioning

confidence: 99%

Early warning of telecom enterprise customer churn based on ensemble learning

Zhou,

Chen,

Sun

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Analyzing customers’ characteristics and giving the early warning of customer churn based on machine learning algorithms, can help enterprises provide targeted marketing strategies and personalized services, and save a lot of operating costs. Data cleaning, oversampling, data standardization and other preprocessing operations are done on 900,000 telecom customer personal characteristics and historical behavior data set based on Python language. Appropriate model parameters were selected to build BPNN (Back Propagation Neural Network). Random Forest (RF) and Adaboost, the two classic ensemble learning models were introduced, and the Adaboost dual-ensemble learning model with RF as the base learner was put forward. The four models and the other four classical machine learning models-decision tree, naive Bayes, K-Nearest Neighbor (KNN), Support Vector Machine (SVM) were utilized respectively to analyze the customer churn data. The results show that the four models have better performance in terms of recall rate, precision rate, F1 score and other indicators, and the RF-Adaboost dual-ensemble model has the best performance. Among them, the recall rates of BPNN, RF, Adaboost and RF-Adaboost dual-ensemble model on positive samples are respectively 79%, 90%, 89%,93%, the precision rates are 97%, 99%, 98%, 99%, and the F1 scores are 87%, 95%, 94%, 96%. The RF-Adaboost dual-ensemble model has the best performance, and the three indicators are 10%, 1%, and 6% higher than the reference. The prediction results of customer churn provide strong data support for telecom companies to adopt appropriate retention strategies for pre-churn customers and reduce customer churn.

show abstract

Section: Plos Onementioning

confidence: 99%

Early warning of telecom enterprise customer churn based on ensemble learning

Zhou,

Chen,

Sun

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Many scholars have conducted relevant research on this issue. Jiang et al [4] constructed a financial crisis warning indicator system from five aspects: profitability, debt repayment ability, development ability, operational ability, and cash flow ability, based on the operating conditions of listed companies. In addition, a financial management early warning model based on BP neural network algorithm has been established.…”

Section: Introductionmentioning

confidence: 99%

An Improved C4.5 Algorithm Shannon Information Theory-Based to Optimize Financial Early Warning System

Dong,

Qi,

Yang

2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

At present, facing massive financial data, it is impossible to effectively classify the characteristics of financial data, and there is a problem of low accuracy of financial early warning. Therefore, this paper proposed a financial early warning system based on the improved C4.5 algorithm. First, the traditional C4.5 algorithm is used to preprocess the original financial data to reduce the redundancy of data attributes. On this basis, C4.5 algorithm is improved by integrating with Shannon’s Information theory, transforming attributes with performance patterns into interval values, classifying different financial status data, constructing decision trees, and designing a financial early warning system. Experimental simulations have shown that the designed financial early warning system has high practical value.

show abstract

“…Machine learning [3] has been applied to risk assessment [4], financial performance [5], fault network management [6], and other fields due to its ability to constantly learn and adapt to the development of enterprises.…”

Section: Introductionmentioning

confidence: 99%

Methods to Improve Company Maturity Based on Analytic Hierarchy Process, Entropy Weight Method and Visual Radar Map

Wang

2023

Advances in Economics, Business and Management Research

View full text Add to dashboard Cite

With the development of 5G, the Internet of Things, and other technologies, data needs to be analyzed and sorted in a larger way, so as to obtain more valuable information from it. In order to address the problem that the maturity of different companies is difficult to analyze due to business factors, in this paper, we show the AHP-EWM combined weight analysis method and visual radar to find the model of the optimal solution, and design a system of maturity index that is suitable for companies. Subsequently, the degree of KPI of the company is shown through a radar map, and find out the optimal direction of the internal system of enterprise development. By increasing the weight ratio of optimal development factors, the maturity of the company can be improved. Finally, this model is used to simulate the application degree of port industries of different sizes and different enterprises. The results of the radar map show that even enterprises of different sizes and properties can be normalized by this model according to their internal KPIs, and the optimization suggestions given by the radar map can improve the maturity of the company, which is of great significance for the company to integrate internal resources and find the development direction of the company.

show abstract

Construction and Application of the Financial Early-Warning Model Based on the BP Neural Network

Cited by 6 publications

References 17 publications

Early warning of telecom enterprise customer churn based on ensemble learning

Early warning of telecom enterprise customer churn based on ensemble learning

An Improved C4.5 Algorithm Shannon Information Theory-Based to Optimize Financial Early Warning System

Methods to Improve Company Maturity Based on Analytic Hierarchy Process, Entropy Weight Method and Visual Radar Map

Contact Info

Product

Resources

About