Machine learning-driven credit risk: a systemic review
Open accessThe DOI matches its Crossref record; 73 of the 73 references it cites were found in a registry or an index.
Abstract
Credit risk assessment is at the core of modern economies. Traditionally, it is measured by statistical methods and manual auditing. Recent advances in financial artificial intelligence stemmed from a new wave of machine learning (ML)-driven credit risk models that gained tremendous attention from both industry and academia. In this paper, we systematically review a series of major research contributions (76 papers) over the past eight years using statistical, machine learning and deep learning techniques to address the problems of credit risk. Specifically, we propose a novel classification methodology for ML-driven credit risk algorithms and their performance ranking using public datasets. We further discuss the challenges including data imbalance, dataset inconsistency, model transparency, and inadequate utilization of deep learning models. The results of our review show that: 1) most deep learning models outperform classic machine learning and statistical algorithms in credit risk estimation, and 2) ensemble methods provide higher accuracy compared with single models. Finally, we present summary tables in terms of datasets and proposed models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 3×
“Typical examples include DTs [27–29], Random Forests (RFs) [4], Classification and Regression Trees (CART) [45], C4.5 [46], and Diverse Ensemble Creation by Oppositional Relabeling of Artificial Training Examples (DECORATE) [47].”
BackgroundMethodCortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Quinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439 · cited 2×
“Typical examples include DTs [27–29], Random Forests (RFs) [4], Classification and Regression Trees (CART) [45], C4.5 [46], and Diverse Ensemble Creation by Oppositional Relabeling of Artificial Training Examples (DECORATE) [47].”
BackgroundA decision-theoretic generalization of on-line learning and an application to boosting
Freund, Y., & Schapire, R. E. (1997) · Journal of Computer and System Sciences · doi:10.1006/jcss.1997.1504 · Cited by 20,466
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
Nearest neighbor pattern classification
Cover, T., & Hart, P. (1967) · IEEE Transactions on Information Theory · doi:10.1109/tit.1967.1053964 · Cited by 16,936 · cited 3×
“The traditional machine learning models for credit risk contain Support Vector Machines (SVMs) [5], k-Nearest Neighbor (k-NN) [3], Random Forests (RFs) [4], Decision Trees (DTs) [27–29], AdaBoost [30], Extreme Gradient Boost (XGBoost) [31], Stochastic Gradient Boosting (SGB) [32], Bagging [33],…”
BackgroundMethodA fast learning algorithm for deep belief nets
Hinton, G. E., Osindero, S., & Teh, Y.-W. (2006) · Neural Computation · doi:10.1162/neco.2006.18.7.1527 · Cited by 16,336 · cited 4×
“Hinton et al. introduced DBNs [37] which are a class of deep neural networks.”
BackgroundInfluentialBreiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325 · cited 2×
“…Vector Machines (SVMs) [5], k-Nearest Neighbor (k-NN) [3], Random Forests (RFs) [4], Decision Trees (DTs) [27–29], AdaBoost [30], Extreme Gradient Boost (XGBoost) [31], Stochastic Gradient Boosting (SGB) [32], Bagging [33], Extreme Learning Machine (ELM) [34] and GA (Genetic Algorithm) [35].”
BackgroundExtreme learning machine: Theory and applications
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006) · Neurocomputing · doi:10.1016/j.neucom.2005.12.126 · Cited by 13,285 · cited 3×
“…Vector Machines (SVMs) [5], k-Nearest Neighbor (k-NN) [3], Random Forests (RFs) [4], Decision Trees (DTs) [27–29], AdaBoost [30], Extreme Gradient Boost (XGBoost) [31], Stochastic Gradient Boosting (SGB) [32], Bagging [33], Extreme Learning Machine (ELM) [34] and GA (Genetic Algorithm) [35].”
BackgroundMethodBackpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891 · cited 2×
“Most of them include Convolutional Neural Networks (CNNs) [36], Deep Belief Neural Networks (DBNs) [37], Artificial Neural Networks (ANNs) [38], LSTM (Long Short-Term Memory) [39], Restricted Boltzmann Machines (RBMs) [40], Deep Multi-Layer Perceptron (DMLP) [41], and Recurrent Neural Networks…”
BackgroundElman, J. L. (1990) · Cognitive Science · doi:10.1207/s15516709cog1402_1 · Cited by 11,212 · cited 1×
“…them include Convolutional Neural Networks (CNNs) [36], Deep Belief Neural Networks (DBNs) [37], Artificial Neural Networks (ANNs) [38], LSTM (Long Short-Term Memory) [39], Restricted Boltzmann Machines (RBMs) [40], Deep Multi-Layer Perceptron (DMLP) [41], and Recurrent Neural Networks (RNNs) [42].”
BackgroundFriedman, J. H. (2002) · Computational Statistics & Data Analysis · doi:10.1016/s0167-9473(01)00065-2 · Cited by 7,067 · cited 4×
“Typical examples include Extreme learning machines (ELM) [7], Ensemble of classifiers [8], Bayesian networks [12], Deep Genetic Cascade Ensembles [11], a hybrid model with convolutional neural networks and Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning…”
BackgroundMethodInfluentialHarris hawks optimization: Algorithm and applications
Heidari, A. A., Mirjalili, S., Faris, H., Aljarah, I., Mafarja, M., & Chen, H. (2019) · Future Generation Computer Systems · doi:10.1016/j.future.2019.02.028 · Cited by 6,324 · cited 1×
“…optimization) MBO [105], (earthworm optimization algorithm) EOA [106], (elephant herding optimization) EHO [107], (moth search algorithm) MS [108], (Slime mould algorithm) SMA [109], (hunger games search) HGS [110], (colony predation algorithm) CPA [111] and (Harris hawks optimization) HHO [112].”
Slime mould algorithm: A new method for stochastic optimization
Li, S., Chen, H., Wang, M., Heidari, A. A., & Mirjalili, S. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.03.055 · Cited by 3,036 · cited 1×
“…optimization) MBO [105], (earthworm optimization algorithm) EOA [106], (elephant herding optimization) EHO [107], (moth search algorithm) MS [108], (Slime mould algorithm) SMA [109], (hunger games search) HGS [110], (colony predation algorithm) CPA [111] and (Harris hawks optimization) HHO [112].”
The Regression Analysis of Binary Sequences
Cox, D. R. (1958) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1958.tb00292.x · Cited by 2,813 · cited 4×
“The model shows an accuracy which is far beyond SVM and Logistic Regression.”
MethodInfluentialMonarch butterfly optimization
Wang, G.-G., Deb, S., & Cui, Z. (2019) · Neural Computing and Applications · doi:10.1007/s00521-015-1923-y · Cited by 983 · cited 2×
“Moreover, in recent years, some authors proposed a series of representative nature-inspired metaheuristic algorithms such as (monarch butterfly optimization) MBO [105], (earthworm optimization algorithm) EOA [106], (elephant herding optimization) EHO [107], (moth search algorithm) MS [108], (Slime mould algorithm) SMA…”
BackgroundMachine learning models and bankruptcy prediction
Barboza, F., Kimura, H., & Altman, E. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.04.006 · Cited by 947 · cited 1×
“A series of machine learning methods are enforced to predict bank-ruptcy [16, 81].”
MethodMoth search algorithm: a bio-inspired metaheuristic algorithm for global optimization problems
Wang, G.-G. (2018) · Memetic Computing · doi:10.1007/s12293-016-0212-3 · Cited by 780 · cited 1×
“Moreover, in recent years, some authors proposed a series of representative nature-inspired metaheuristic algorithms such as (monarch butterfly optimization) MBO [105], (earthworm optimization algorithm) EOA [106], (elephant herding optimization) EHO [107], (moth search algorithm) MS [108], (Slime mould algorithm) SMA…”
BackgroundWang, G.-G., Deb, S., & Coelho, L. D. S. (2015) · 2015 3rd International Symposium on Computational and Business Intelligence (ISCBI) · doi:10.1109/iscbi.2015.8 · Cited by 672 · cited 2×
“Moreover, in recent years, some authors proposed a series of representative nature-inspired metaheuristic algorithms such as (monarch butterfly optimization) MBO [105], (earthworm optimization algorithm) EOA [106], (elephant herding optimization) EHO [107], (moth search algorithm) MS [108], (Slime mould algorithm) SMA…”
BackgroundThe Colony Predation Algorithm
Tu, J., Chen, H., Wang, M., & Gandomi, A. H. (2021) · Journal of Bionic Engineering · doi:10.1007/s42235-021-0050-y · Cited by 571 · cited 1×
“…optimization) MBO [105], (earthworm optimization algorithm) EOA [106], (elephant herding optimization) EHO [107], (moth search algorithm) MS [108], (Slime mould algorithm) SMA [109], (hunger games search) HGS [110], (colony predation algorithm) CPA [111] and (Harris hawks optimization) HHO [112].”
Machine Learning in Banking Risk Management: A Literature Review
Leo, M., Sharma, S., & Maddulety, K. (2019) · Risks · doi:10.3390/risks7010029 · Cited by 461 · cited 1×
“In [101], similar problems with [98] occurred.”
Genetic algorithm-based heuristic for feature selection in credit risk assessment
Oreski, S., & Oreski, G. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.09.004 · Cited by 430 · cited 1×
“…risk model [13], Artificial Neural Network [15], LSTM and AdaBoost [9], denoising-based neural network [21], deep belief network [14, 75], probabilistic neural network (PNN) [76], Genetic algorithm with neural network [77], CNN [78] all show their great competency in estimation and assessing.”
MethodA neural network approach for credit risk evaluation
Angelini, E., di Tollo, G., & Roli, A. (2008) · The Quarterly Review of Economics and Finance · doi:10.1016/j.qref.2007.04.001 · Cited by 349 · cited 1×
“Two-layer additive risk model [13], Artificial Neural Network [15], LSTM and AdaBoost [9], denoising-based neural network [21], deep belief network [14, 75], probabilistic neural network (PNN) [76], Genetic algorithm with neural network [77], CNN [78] all show their great competency in estimation…”
MethodZhang, X., Han, Y., Xu, W., & Wang, Q. (2021) · Information Sciences · doi:10.1016/j.ins.2019.05.023 · Cited by 283 · cited 1×
“Recurrent Neural Network (RNN) [65], Boosted Decision Tree [66–68], a deep learning structure with an advanced feature engineering [69] display a satisfactory performance.”
BackgroundGalindo, J., & Tamayo, P. (2000) · Computational Economics · doi:10.1023/a:1008699112516 · Cited by 254 · cited 2×
“[26] Mortgage loan data from a commercial bank CART 0.”
BackgroundMethodA comparative study on base classifiers in ensemble methods for credit scoring
Abellán, J., & Castellano, J. G. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.12.020 · Cited by 248
Machine learning techniques for credit risk evaluation: a systematic literature review
Bhatore, S., Mohan, L., & Reddy, Y. R. (2020) · Journal of Banking and Financial Technology · doi:10.1007/s42786-020-00020-3 · Cited by 224 · cited 1×
“Siddharth Bhatore et al. [100] displayed an intact review of machine learning in credit risk and showed clear graphs, but they ignored the limitation of datasets in some sense.”
Background(2019) · Elsevier eBooks · doi:10.1016/c2016-1-05231-8 · Cited by 198
A deep learning approach for credit scoring using credit default swaps
Luo, C., Wu, D., & Wu, D. (2017) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2016.12.002 · Cited by 196 · cited 1×
“Two-layer additive risk model [13], Artificial Neural Network [15], LSTM and AdaBoost [9], denoising-based neural network [21], deep belief network [14, 75], probabilistic neural network (PNN) [76], Genetic algorithm with neural network [77], CNN [78] all show their great competency in estimation…”
MethodPredicting Credit Risk in Peer-to-Peer Lending: A Neural Network Approach
Byanjankar, A., Heikkila, M., & Mezei, J. (2015) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2015.109 · Cited by 189 · cited 7×
“[17] A leading European P2P Platform Bondora Neural networks 0.”
BackgroundMethodInfluentialAn Investigation of Credit Card Default Prediction in the Imbalanced Datasets
Alam, T. M., Shaukat, K., Hameed, I. A., Luo, S., Sarwar, M. U., Shabbir, S., Li, J., & Khushi, M. (2020) · IEEE Access · doi:10.1109/access.2020.3033784 · Cited by 187 · cited 1×
“Recurrent Neural Network (RNN) [65], Boosted Decision Tree [66–68], a deep learning structure with an advanced feature engineering [69] display a satisfactory performance.”
BackgroundExtreme learning machines for credit scoring: An empirical evaluation
Bequé, A., & Lessmann, S. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.05.050 · Cited by 174 · cited 5×
“Typical examples include Extreme learning machines (ELM) [7], Ensemble of classifiers [8], Bayesian networks [12], Deep Genetic Cascade Ensembles [11], a hybrid model with convolutional neural networks and Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning…”
MethodInfluentialSupervised Machine Learning Algorithms for Credit Card Fraud Detection: A Comparison
Khatri, S., Arora, A., & Agrawal, A. P. (2020) · International Conference on Cloud Computing, Data Science & Engineering (Confluence) · doi:10.1109/confluence47617.2020.9057851 · Cited by 174 · cited 2×
“In [71–73], the authors implemented LR, SVM, k-NN, NB, RF, DT, MLP methods and found that they were all robust while tree-related models have the best performance.”
MethodMultiple classifier application to credit risk assessment
Twala, B. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2009.10.018 · Cited by 166 · cited 1×
“machines (ELM) [7], Ensemble of classifiers [8], Bayesian networks [12], Deep Genetic Cascade Ensembles [11], a hybrid model with convolutional neural networks and Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning and statistical learning [56], Radial Ba…”
MethodA Deep Learning Approach for Credit Scoring of Peer-to-Peer Lending Using Attention Mechanism LSTM
Wang, C., Han, D., Liu, Q., & Luo, S. (2018) · IEEE Access · doi:10.1109/access.2018.2887138 · Cited by 156 · cited 5×
“Two-layer additive risk model [13], Artificial Neural Network [15], LSTM and AdaBoost [9], denoising-based neural network [21], deep belief network [14, 75], probabilistic neural network (PNN) [76], Genetic algorithm with neural network [77], CNN [78] all show their great competency in estimation and assessing.”
BackgroundMethodInfluentialGarcía, V., Marqués, A. I., & Sánchez, J. S. (2018) · Information Fusion · doi:10.1016/j.inffus.2018.07.004 · Cited by 154
Wan, S., Liang, Y., Zhang⋆, Y., & Guizani, M. (2018) · IEEE Access · doi:10.1109/access.2018.2851382 · Cited by 146 · cited 1×
“…them include Convolutional Neural Networks (CNNs) [36], Deep Belief Neural Networks (DBNs) [37], Artificial Neural Networks (ANNs) [38], LSTM (Long Short-Term Memory) [39], Restricted Boltzmann Machines (RBMs) [40], Deep Multi-Layer Perceptron (DMLP) [41], and Recurrent Neural Networks (RNNs) [42].”
BackgroundE.T.-RNN: Applying Deep Learning to Credit Loan Applications
Babaev, D., Savchenko, M., Tuzhilin, A., & Umerenkov, D. (2019) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3292500.3330693 · Cited by 140
Credit Card Fraud Detection Based on Machine and Deep Learning
Najadat, H., Altiti, O., Aqouleh, A. A., & Younes, M. B. (2020) · International Conference on Information and Communication Systems (ICICS) · doi:10.1109/icics49469.2020.239524 · Cited by 136 · cited 1×
“[103] ?”
Niu, K., Zhang, Z., Liu, Y., & Li, R. (2020) · Information Sciences · doi:10.1016/j.ins.2020.05.040 · Cited by 125 · cited 1×
“Neural Networks [17, 82, 83], Attention Mechanism LSTM [20], word embedding models [84], Ensemble Learning Method [85, 86], Restricted Boltzmann Machine (RBM) [87] all exert their impact on predicting the risk of P2P industry.”
MethodEnterprise credit risk evaluation based on neural network algorithm
Huang, X., Liu, X., & Ren, Y. (2018) · Cognitive Systems Research · doi:10.1016/j.cogsys.2018.07.023 · Cited by 124 · cited 1×
“…risk model [13], Artificial Neural Network [15], LSTM and AdaBoost [9], denoising-based neural network [21], deep belief network [14, 75], probabilistic neural network (PNN) [76], Genetic algorithm with neural network [77], CNN [78] all show their great competency in estimation and assessing.”
MethodNetwork based credit risk models
Giudici, P., Misheva, B. H., & Spelta, A. (2019) · Quality Engineering · doi:10.1080/08982112.2019.1655159 · Cited by 120 · cited 1×
“Neural Networks [17, 82, 83], Attention Mechanism LSTM [20], word embedding models [84], Ensemble Learning Method [85, 86], Restricted Boltzmann Machine (RBM) [87] all exert their impact on predicting the risk of P2P industry.”
MethodMaking Deep Learning-Based Predictions for Credit Scoring Explainable
Dastile, X., & Çelik, T. (2021) · IEEE Access · doi:10.1109/access.2021.3068854 · Cited by 113 · cited 7×
“Typical examples include Extreme learning machines (ELM) [7], Ensemble of classifiers [8], Bayesian networks [12], Deep Genetic Cascade Ensembles [11], a hybrid model with convolutional neural networks and Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning…”
MethodInfluentialSong, Y. P., Wang, Y., Ye, X., Wang, D., Yin, Y., & Wang, Y. (2020) · Information Sciences · doi:10.1016/j.ins.2020.03.027 · Cited by 110 · cited 1×
“Neural Networks [17, 82, 83], Attention Mechanism LSTM [20], word embedding models [84], Ensemble Learning Method [85, 86], Restricted Boltzmann Machine (RBM) [87] all exert their impact on predicting the risk of P2P industry.”
MethodRushin, G., Stancil, C., Sun, M., Adams, S., & Beling, P. A. (2017) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds.2017.7937700 · Cited by 110 · cited 2×
“By using an auto-encoder, the authors in [70] create features with domain expertise.”
MethodClassification Restricted Boltzmann Machine for comprehensible credit scoring model
Tomczak, J. M., & Zięba, M. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.10.016 · Cited by 109 · cited 7×
“Similarly, we sort and calculate the mean ACC and AUC appearing in the Australian Credit Risk dataset.”
BackgroundInfluentialCredit risk modeling using Bayesian network with a latent variable
Masmoudi, K., Abid, L., & Masmoudi, A. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.03.014 · Cited by 90 · cited 1×
“In [52], the Bayesian network method is improved to find out whether there is a change in credit risk profiles.”
MethodBig Data techniques to measure credit banking risk in home equity loans
Pérez-Martín, A., Pérez-Torregrosa, A., & Vaca, M. (2018) · Journal of business research · doi:10.1016/j.jbusres.2018.02.008 · Cited by 86
Credit Risk Scoring with Bayesian Network Models
Leong, C. K. (2015) · Computational Economics · doi:10.1007/s10614-015-9505-8 · Cited by 86 · cited 2×
“For example, Chee Kian Leong (2015) uses data from a firm in Singapore [12].”
MethodBusiness Analytics using Random Forest Trees for Credit Risk Prediction: A Comparison Study
Ghatasheh, N. (2014) · International Journal of Advanced Science and Technology · doi:10.14257/ijast.2014.72.02 · Cited by 86 · cited 1×
“In [10], random forest trees are proven to outperform most of the other machine learning models.”
BackgroundA hybrid deep learning model for consumer credit scoring
Zhu, B., Yang, W., Wang, H., & Yuan, Y. (2018) · International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd.2018.8396195 · Cited by 77 · cited 2×
“machines (ELM) [7], Ensemble of classifiers [8], Bayesian networks [12], Deep Genetic Cascade Ensembles [11], a hybrid model with convolutional neural networks and Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning and statistical learning [56], Radial Ba…”
BackgroundMethodPredicting Default Risk on Peer-to-Peer Lending Imbalanced Datasets
Chen, Y.-R., Leu, J., Huang, S.-A., Wang, J.-T., & Takada, J. (2021) · IEEE Access · doi:10.1109/access.2021.3079701 · Cited by 75 · cited 6×
“They can better handle sequential information rather than the spatial data which Convolutional Neural Networks (CNNs) can effectively process.”
MethodInfluentialYu, L., Yang, Z., & Tang, L. (2015) · Flexible Services and Manufacturing Journal · doi:10.1007/s10696-015-9226-2 · Cited by 56 · cited 1×
“…additive risk model [13], Artificial Neural Network [15], LSTM and AdaBoost [9], denoising-based neural network [21], deep belief network [14, 75], probabilistic neural network (PNN) [76], Genetic algorithm with neural network [77], CNN [78] all show their great competency in estimation and…”
MethodCredit scoring with a feature selection approach based deep learning
Ha, V.-S., & Nguyen, H.-N. (2016) · MATEC Web of Conferences · doi:10.1051/matecconf/20165405004 · Cited by 55 · cited 1×
“…Cascade Ensembles [11], a hybrid model with convolutional neural networks and Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning and statistical learning [56], Radial Basis Function [57], TreeSHAP method for Stochastic Gradient…”
MethodHybrid Model for Credit Risk Prediction: An Application of Neural Network Approaches
Chi, G., Uddin, M. S., Abedin, M. Z., & Yuan, K. (2019) · International Journal of Artificial Intelligence Tools · doi:10.1142/s0218213019500179 · Cited by 53 · cited 1×
“[102] ?”
Arya, M., & Hanumat Sastry, G. (2020) · Smart Science · doi:10.1080/23080477.2020.1783491 · Cited by 51 · cited 2×
“CCF (Credit card fraud) is a specific crime in the banking system and becoming a substantially growing problem worldwide [64].”
BackgroundMethodReview of Machine Learning models for Credit Scoring Analysis
Kumar, M. R., & Gunjan, V. K. (2020) · Ingenieria Solidaria · doi:10.16925/2357-6014.2020.01.11 · Cited by 50
Hsu, T.-C., Liou, S.-T., Wang, Y.-P., Huang, Y.-S., & Che-Lin (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8682212 · Cited by 49 · cited 1×
“Recurrent Neural Network (RNN) [65], Boosted Decision Tree [66–68], a deep learning structure with an advanced feature engineering [69] display a satisfactory performance.”
BackgroundAn improved SMO algorithm for financial credit risk assessment – Evidence from China’s banking
Zhang, Q., Wang, J., Lu, A., Wang, S., & Ma, J. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.07.002 · Cited by 45 · cited 1×
“[23] The credit data from CBRC, German dataset, Darden datase FV-SMO 0.”
MethodMultiple instance learning for credit risk assessment with transaction data
ZHANG, T., Zhang, W., Xu, W. X., & Hao, H. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.07.030 · Cited by 45 · cited 1×
“…Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning and statistical learning [56], Radial Basis Function [57], TreeSHAP method for Stochastic Gradient Boosting [58], a real-time binary classification model [59], CNN [60], MLP [61], etc.”
MethodSupply Chain Fraud Prediction Based On XGBoost Method
Zhou, Y., Song, X., & Zhou, M. (2021) · International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE) · doi:10.1109/icbaie52039.2021.9389949 · Cited by 40 · cited 2×
“[80] ?”
MethodA Closer Look Into the Characteristics of Fraudulent Card Transactions
Can, B., YAVUZ, A. G., Karslıgil, E., & Guvensan, M. A. (2020) · IEEE Access · doi:10.1109/access.2020.3022315 · Cited by 39 · cited 1×
“In [71–73], the authors implemented LR, SVM, k-NN, NB, RF, DT, MLP methods and found that they were all robust while tree-related models have the best performance.”
MethodTowards An Efficient Real-time Approach To Loan Credit Approval Using Deep Learning
Abakarim, Y., Lahby, M., & Attioui, A. (2018) · International Symposium on Signal, Image, Video and Communications (ISIVC) · doi:10.1109/isivc.2018.8709173 · Cited by 29
A Novel GSCI-Based Ensemble Approach for Credit Scoring
Chen, X., Li, S., Xu, X., Meng, F., & Cao, W. (2020) · IEEE Access · doi:10.1109/access.2020.3043937 · Cited by 28
Learning to Undersampling for Class Imbalanced Credit Risk Forecasting
Chi, J., Zeng, G., Zhong, Q., Liang, T. B., Feng, J., Ao, X., & Tang, J. (2020) · Proceedings · doi:10.1109/icdm50108.2020.00016 · Cited by 25 · cited 1×
“In [63], a unique model named TRUST (Trainable Undersampling with SELF Training) was proved to be decisive.”
MethodEvery Corporation Owns Its Image: Corporate Credit Ratings via Convolutional Neural Networks
Feng, B., Xue, W., Xue, B., & Liu, Z. (2020) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc51575.2020.9344973 · Cited by 24 · cited 2×
“[78] ?”
MethodCredit scoring model: A combination of genetic programming and deep learning
Tran, K. V., Dương, T. L., & Ho, Q. (2016) · Future Technologies Conference · doi:10.1109/ftc.2016.7821603 · Cited by 23 · cited 2×
“Typical examples include Extreme learning machines (ELM) [7], Ensemble of classifiers [8], Bayesian networks [12], Deep Genetic Cascade Ensembles [11], a hybrid model with convolutional neural networks and Relief algorithm [22], Genetic Programming [53], feature selection [54], RNN [55], ensemble of supervised learning…”
MethodA proposal for online analysis and identification of fraudulent financial transactions
Torres, R. A. L., & Ladeira, M. (2020) · International Conference on Machine Learning and Applications · doi:10.1109/icmla51294.2020.00047 · Cited by 18 · cited 1×
“In [74], Visual Analytics were used to help reduce the incidence of false positives.”
MethodA Survey of Applying Machine Learning Techniques for Credit Rating: Existing Models and Open Issues
Wang, X., Xu, M. G., & Pusatli, Ö. T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-26535-3_15 · Cited by 18 · cited 2×
“In [101], similar problems with [98] occurred.”
BackgroundApplication of Deep Learning Neural Network in Online Supply Chain Financial Credit Risk Assessment
Xu, R.-Z., & He, M. (2020) · International Conference on Computer Information and Big Data Applications (CIBDA) · doi:10.1109/cibda50819.2020.00058 · Cited by 17 · cited 1×
“The authors in [24] construct a deep belief network based on Restricted Boltzmann Machine and classifier SOFTMAX.”
MethodAhmed, F., & Shamsuddin, R. (2021) · 2021 2nd International Conference on Computing and Data Science (CDS) · doi:10.1109/cds52072.2021.00026 · Cited by 15 · cited 1×
“[72] ?”
Big data in healthcare applications
Liu, S., McGree, J. M., Ge, Z., & Xie, Y. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-803732-4.00007-6 · Cited by 13
Cited by
Talaat, F. M., Aljadani, A., Badawy, M., & Elhosseini, M. (2024) · Neural Computing and Applications · doi:10.1007/s00521-023-09232-2 · Cited by 105
FBLearn: Decentralized Platform for Federated Learning on Blockchain
Djolev, D., Lazarova, M., & Nakov, O. (2024) · Electronics · doi:10.3390/electronics13183672 · Cited by 5
Metadata
- Authors
- Shi, S., Tse, R., Luo, W., D’Addona, S., & Pau, G.
- Venue
- Neural Computing and Applications
- Published
- 2022-07-16
- Volume
- 34
- Issue
- 17
- Pages
- 14327-14339
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W4285588387
- Cited by
- 193
- References
- 73
- FWCI
- 63.03
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.