A Sparsity Algorithm with Applications to Corporate Credit Rating

In Artificial Intelligence, interpreting the results of a Machine Learning technique often termed as a black box is a difficult task. A counterfactual explanation of a particular “black box” attempts to find the smallest change to the input values that modifies the prediction to a particular output, other than the original one. In this work we formulate the problem of finding a counterfactual explanation as an optimization problem. We propose a new “sparsity algorithm” which solves the optimization problem, while also maximizing the sparsity of the counterfactual explanation. We apply the sparsity algorithm to provide a simple suggestion to publicly traded companies in order to improve their credit ratings. We validate the sparsity algorithm with a synthetically generated dataset and we further apply it to quarterly financial statements from companies in financial, healthcare and IT sectors of the US market. We provide evidence that the counterfactual explanation can capture the nature of the real statement features that changed between the current quarter and the following quarter when ratings improved. The empirical results show that the higher the rating of a company the greater the “effort” required to further improve credit rating.

[1]  Denali Molitor,et al.  Model Agnostic Supervised Local Explanations , 2018, NeurIPS.

[2]  Adnan Khashman,et al.  Neural networks for credit risk evaluation: Investigation of different neural models and learning schemes , 2010, Expert Syst. Appl..

[3]  Ivan W. Selesnick,et al.  Sparse Regularization via Convex Analysis , 2017, IEEE Transactions on Signal Processing.

[4]  David West,et al.  Neural network credit scoring models , 2000, Comput. Oper. Res..

[5]  Michael Elad,et al.  From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images , 2009, SIAM Rev..

[6]  Kuldeep Kumar,et al.  Forecasting credit ratings using an ANN and statistical techniques , 2003 .

[7]  Freddy Lécué,et al.  Interpretable Credit Application Predictions With Counterfactual Explanations , 2018, NIPS 2018.

[8]  Fabian Dittrich.  The Credit Rating Industry: Competition and Regulation , 2007 .

[9]  Bertrand K. Hassani,et al.  Credit Risk Analysis Using Machine and Deep Learning Models , 2018 .

[10]  Petr Hájek,et al.  Predicting Firms' Credit Ratings Using Ensembles of Artificial Immune Systems and Machine Learning - An Over-Sampling Approach , 2014, AIAI.

[11]  Bernard Ghanem,et al.  Sparsity Constrained Minimization via Mathematical Programming with Equilibrium Constraints , 2016, 1608.04430.

[12]  Kuldeep Kumar,et al.  Credit Rating Forecasting Using Machine Learning Techniques , 2019, Advances in Data Mining and Database Management.

[13]  Dan Wang,et al.  Application of Deep Neural Networks to assess corporate Credit Rating , 2020, ArXiv.

[14]  Nishant Shukla.  Machine Learning with TensorFlow , 2018 .

[15]  KangByeong Ho,et al.  Investigation and improvement of multi-layer perceptron neural networks for credit scoring , 2015 .

[16]  Douglas Kline,et al.  Revisiting squared-error and cross-entropy functions for training neural network classifiers , 2005, Neural Computing & Applications.

[17]  Kuldeep Kumar,et al.  Artificial neural network vs linear discriminant analysis in credit ratings forecast: A comparative study of prediction performances , 2006 .

[18]  Alexander Mordvintsev,et al.  Inceptionism: Going Deeper into Neural Networks , 2015 .

[19]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[20]  Jiang Bian,et al.  Causal inference and counterfactual prediction in machine learning for actionable healthcare , 2020, Nature Machine Intelligence.

[21]  H. B. Curry.  The method of steepest descent for non-linear minimization problems , 1944 .

[22]  Hyunchul Ahn,et al.  Corporate Credit Rating using Multiclass Classification Models with order Information , 2011 .

[23]  Petr Hájek,et al.  Credit rating modelling by kernel-based approaches with supervised and semi-supervised learning , 2011, Neural Computing and Applications.

[24]  Linfeng Chen,et al.  Bond yield and credit rating: evidence of Chinese local government financing vehicles , 2019 .

[25]  So Young Sohn,et al.  Support vector machines for default prediction of SMEs based on technology credit , 2010, Eur. J. Oper. Res..

[26]  Soushan Wu,et al.  Credit rating analysis with support vector machines and neural networks: a market comparative study , 2004, Decis. Support Syst..

[27]  Feiping Nie,et al.  Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Exact Top-k Feature Selection via ℓ2,0-Norm Constraint , 2022 .

[28]  Alun D. Preece,et al.  Interpretability of deep learning models: A survey of results , 2017, 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computed, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI).

[29]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[30]  Jinyu Li,et al.  A Multiclass Machine Learning Approach to Credit Rating Prediction , 2008, 2008 International Symposiums on Information Processing.

[31]  Younes Boujelbene,et al.  Credit risk prediction: A comparative study between discriminant analysis and the neural network approach , 2015 .

[32]  Dacheng Tao,et al.  Top-k Feature Selection Framework Using Robust 0–1 Integer Programming , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Chris Russell,et al.  Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR , 2017, ArXiv.

[34]  Wojciech Czarnecki,et al.  On Loss Functions for Deep Neural Networks in Classification , 2017, ArXiv.

[35]  Ionuct Florescu,et al.  A comparative study of forecasting Corporate Credit Ratings using Neural Networks, Support Vector Machines, and Decision Trees , 2020, The North American Journal of Economics and Finance.

[36]  Po-Sen Huang,et al.  Reducing Sentiment Bias in Language Models via Counterfactual Evaluation , 2019, FINDINGS.

[37]  Jaime S. Cardoso,et al.  Machine Learning Interpretability: A Survey on Methods and Metrics , 2019, Electronics.

[38]  Agustí Verde Parera,et al.  General data protection regulation , 2018 .

[39]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[40]  Chandan Singh,et al.  Definitions, methods, and applications in interpretable machine learning , 2019, Proceedings of the National Academy of Sciences.

[41]  Dan Wang,et al.  Is Image Encoding Beneficial for Deep Learning in Finance? An Analysis of Image Encoding Methods for the Application of Convolutional Neural Networks in Finance , 2020, ArXiv.

[42]  Ziyan Wu,et al.  Counterfactual Visual Explanations , 2019, ICML.