A neural network approach for credit risk evaluation

By Eliana Angelini, Giacomo di Tollo, Andrea Roli. 2008

379 citations recorded by the source corpus.

Subfields: Accounting, Finance, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/99c245dd73f47ccedf36be3f7d9221273506dc82

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Accounting

1. Sid Bundy
2. William Eberle
3. Sheikh Rabiul Islam
4. József Mezei
5. Sheikh Khaled Ghafoor
6. Hamido Fujita
7. Jie Lang
8. Arash Bahrammirzaee

In Finance

1. Sid Bundy
2. William Eberle
3. Sheikh Rabiul Islam
4. József Mezei
5. Sheikh Khaled Ghafoor
6. Hamido Fujita
7. Jie Lang
8. Arash Bahrammirzaee

In Ocean Engineering

1. József Mezei
2. Arash Bahrammirzaee
3. Ajay Byanjankar
4. Markku Heikkilä

Citations in the corpus

• A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems (2010, methodology): “[35] developed two NN systems, one with a standard feed-forward network and other one with special purpose architecture.”
• Predicting Credit Risk in Peer-to-Peer Lending: A Neural Network Approach (2015, methodology): “Neural networks are typically applied to efficiently and effectively perform tasks, such as classification, pattern recognition, optimization, clustering and prediction [6,22,23].”
• Infusing domain knowledge in AI-based "black box" models for better explainability with application in bankruptcy prediction (2019, background): “To asses credit risk by human experts, the 5C’s of credit is commonly used to analyze key factors: character (reputation of the borrower/firm), capital (leverage), capacity (volatility of the borrower’s earnings), collateral (pledged asset) and cycle (macroeconomic) conditions [9, 19].”
• Gazelle: A Low Latency Framework for Secure Neural Network Inference (2018, background): “rithms and extensive computational resources, modern machine learning has found surprising applications in such diverse domains as medical diagnosis [12], [39], facial recognition [35] and credit risk assessment [2].”
• Imbalanced enterprise credit evaluation with DTE-SBD: Decision tree ensemble based on SMOTE and bagging with differentiated sampling rates (2018, methodology): “Neural network is widely used for enterprise credit evaluation modeling [3, 20, 35].”
• Oblivious Neural Network Predictions via MiniONN Transformations (2017, neutral): “Machine learning is now used extensively in many application domains such as pattern recognition [10], medical diagnosis [25] and credit-risk assessment [3].”