International Journal of Statistical Distributions and Applications最新文献

Credit Risk Modelling Using RNN-LSTM Hybrid Model for Digital Financial Institutions 利用 RNN-LSTM 混合模型为数字金融机构建立信用风险模型

International Journal of Statistical Distributions and Applications Pub Date : 2024-04-11 DOI: 10.11648/j.ijsd.20241002.11

Gabriel Musyoka, Antony Waititu, Herbert Imboga

{"title":"Credit Risk Modelling Using RNN-LSTM Hybrid Model for Digital Financial Institutions","authors":"Gabriel Musyoka, Antony Waititu, Herbert Imboga","doi":"10.11648/j.ijsd.20241002.11","DOIUrl":"https://doi.org/10.11648/j.ijsd.20241002.11","url":null,"abstract":"In response to the rapidly evolving financial market and the escalating concern surrounding credit risk in digital financial institutions, this project addresses the urgency for accurate credit risk prediction models. Traditional methods such as Neural network models, kernel-based virtual machines, Z-score, and Logit (logistic regression model) have all been used, but their results have proven less than satisfactory. The project focuses on developing a credit scoring model specifically tailored for digital financial institutions, by leveraging a hybrid model that combines long short-term memory (LSTM) networks with recurrent neural networks (RNN). This innovative approach capitalizes on the strengths of the Long-Short Term Memory (LSTM) for long-term predictions and Recurrent Neural Network (RNN) for its recurrent neural network capabilities. A key component of the approach is feature selection, which entails extracting a subset of pertinent features from the credit risk data using RNN in order to help classify loan applications. The researcher chose to use data from Kaggle to study and compare the efficacy of different models. The findings reveal that the RNN-LSTM hybrid model outperforms other RNNs, LSTMs, and traditional models. Specifically, the hybrid model demonstrated distinct advantages, showcasing higher accuracy and a superior Area Under the Curve (AUC) compared to individual RNN and LSTM models. While RNN and LSTM models exhibited slightly lower accuracy individually, their combination in the hybrid model proved to be the optimal choice. In summary, the RNN-LSTM hybrid model developed stands out as the most effective solution for predicting credit risk in digital financial institutions, surpassing the performance of standalone RNN and LSTM models as well as traditional methodologies. This research contributes valuable insights for banks, regulators, and investors seeking robust credit risk assessment tools in the dynamic landscape of digital finance.","PeriodicalId":427819,"journal":{"name":"International Journal of Statistical Distributions and Applications","volume":"109 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140713499","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}

引用次数: 0

Investigating the Impact of Variable Dividends and Tail Dependence in a Compound Poisson Risk Model 调查复合泊松风险模型中可变股息和尾部依赖性的影响

International Journal of Statistical Distributions and Applications Pub Date : 2024-01-18 DOI: 10.11648/j.ijsd.20241001.11

Kiswendsida Mahamoudou Ouedraogo, Delwendé Abdoul-Kabir Kafando, François Xavier Ouedraogo, Pierre Clovis Nitiéma

引用次数: 0

Synthesis of C4 Olefin by Ethanol Coupling Based on Multivariate Statistical Analysis 基于多元统计分析的乙醇偶联合成 C4 烯烃技术

International Journal of Statistical Distributions and Applications Pub Date : 2023-12-11 DOI: 10.11648/j.ijsd.20230904.11

Hua Xu

引用次数: 0

Mixed Autoregressive Model for Spatial Data: A Bayesian Application to Poverty Mapping 空间数据的混合自回归模型：贫困绘图的贝叶斯应用

International Journal of Statistical Distributions and Applications Pub Date : 2023-10-31 DOI: 10.11648/j.ijsd.20230903.12

Alexander Kwaku Boateng, Richard Puurbalanta, Gideon Mensah Engmann, Ernest Zamanah, Angela Osei-Mainoo

引用次数: 0

Modelling Count Data for HIV-Positive Patients on Antiretroviral Treatment in Kenya 肯尼亚接受抗逆转录病毒治疗的艾滋病毒阳性患者计数数据建模

International Journal of Statistical Distributions and Applications Pub Date : 2023-10-31 DOI: 10.11648/j.ijsd.20230903.11

Anna Nanjala Muricho, Thomas Mageto, S. Mwalili

引用次数: 0

Bayes Estimator Parameters Exponential Distribution of Type I Sensor Data Using Linear Exponential Loss Function Method Based on Prior Jeffrey 基于先验Jeffrey的线性指数损失函数法估计I型传感器数据的Bayes参数指数分布

International Journal of Statistical Distributions and Applications Pub Date : 2023-07-11 DOI: 10.11648/j.ijsd.20230902.12

null Afriani, Ardi Kurniawan, E. Ana

引用次数: 0

Variable Selection for Semi-Parametric Models with Interaction Under High Dimensional Data 高维数据下具有交互作用的半参数模型的变量选择

International Journal of Statistical Distributions and Applications Pub Date : 2023-04-15 DOI: 10.11648/j.ijsd.20230902.11

Ya-Feng Xia, Na Kui

引用次数: 0

Bayesian Analysis on the Spatial Difference of Input Risk of Overseas Cases of COVID-19 in China 中国境外新冠肺炎病例输入风险空间差异的贝叶斯分析

International Journal of Statistical Distributions and Applications Pub Date : 2023-03-31 DOI: 10.11648/j.ijsd.20230901.15

Bo Yang, Yunyuan Yang, W. Zheng, Yanmei Li, Xinping Yang

引用次数: 0

Bayesian Multiple Linear Regression Model for GDP in Nepal 尼泊尔GDP的贝叶斯多元线性回归模型

International Journal of Statistical Distributions and Applications Pub Date : 2023-02-27 DOI: 10.11648/j.ijsd.20230901.12

Ranjita Pandey, Dipendra Bahadur Chand, H. Tolani

引用次数: 0

Analyzing Dynamic Regimes of GARCH Model on Stock Price Volatility 股票价格波动GARCH模型的动态机制分析

International Journal of Statistical Distributions and Applications Pub Date : 2023-02-27 DOI: 10.11648/j.ijsd.20230901.13

Rosemary Ukamaka Okafor, Josephine Nneamaka Onyeka-Ubaka

引用次数: 0