April 11, 2024International Journal of Statistical Distributions and ApplicationsOpen Access

Credit Risk Modelling Using RNN-LSTM Hybrid Model for Digital Financial Institutions

View Full Paper

Ask AI

Bookmark

Authors

GMGabriel MusyokaJomo Kenyatta University of Agriculture and Technology AWAntony G. WaitituJomo Kenyatta University of Agriculture and Technology HIHerbert ImbogaJomo Kenyatta University of Agriculture and Technology

Discussion

Member takes

Implication

Comparative benchmark demonstrates higher accuracy in credit risk prediction for digital financial institutions, highlighting the benefit of hybrid neural architectures.

Key Points

Hybrid RNN-LSTM architectures outperform standalone recurrent neural networks and traditional baseline models in digital credit risk prediction.
The proposed hybrid model achieved higher accuracy and superior area under the curve compared to individual recurrent architectures on Kaggle data.
Feature selection via recurrent neural networks combined with long short-term memory networks supports robust risk assessment for digital banks.

Cite This Study

Musyoka et al. (2024) studied this question.

synapsesocial.com/papers/68e6f968b6db643587673d37 https://doi.org/10.11648/j.ijsd.20241002.11

View Full Paper

Ask AI

Bookmark

Implication

Comparative benchmark demonstrates higher accuracy in credit risk prediction for digital financial institutions, highlighting the benefit of hybrid neural architectures.

Credit Risk Modelling Using RNN-LSTM Hybrid Model for Digital Financial Institutions

Discussion

Member takes

Implication

Key Points

Cite This Study

Credit Risk Modelling Using RNN-LSTM Hybrid Model for Digital Financial Institutions

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider