Sensitivity based Neural Networks Explanations

Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque "black boxes". The difficulty of interpreting the predictions of a neural network often prevents its use in fields where explainability is important, such as the financial industry where regulators and auditors often insist on this aspect. In this paper, we present a way to assess the relative input features importance of a neural network based on the sensitivity of the model output with respect to its input. This method has the advantage of being fast to compute, it can provide both global and local levels of explanations and is applicable for many types of neural network architectures. We illustrate the performance of this method on both synthetic and real data and compare it with other interpretation techniques. This method is implemented into an open-source Python package that allows its users to easily generate and visualize explanations for their neural networks.

[1]  I-Cheng Yeh,et al.  The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients , 2009, Expert Syst. Appl..

[2]  Justin A. Sirignano,et al.  Deep Learning for Mortgage Risk , 2016, Journal of Financial Econometrics.

[3]  Guoqiang Peter Zhang,et al.  Neural networks for classification: a survey , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[4]  Amelia A. Baldwin,et al.  Interpretable credit model development via artificial neural networks , 2007, Intell. Syst. Account. Finance Manag..

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  S. Lipovetsky,et al.  Analysis of regression in game theory approach , 2001 .

[7]  Justin A. Sirignano Deep learning for limit order books , 2016, Quantitative Finance.

[8]  Bryan T. Kelly,et al.  Empirical Asset Pricing Via Machine Learning , 2018, The Review of Financial Studies.

[9]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[10]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[11]  B. Frey,et al.  The human splicing code reveals new insights into the genetic determinants of disease , 2015, Science.

[12]  Mohammad Ghodsi,et al.  Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data , 2005, BMC Medical Informatics Decis. Mak..

[13]  Markus Pelger,et al.  Deep Learning in Asset Pricing , 2019, Manag. Sci..

[14]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[15]  Kay Giesecke,et al.  Significance Tests for Neural Networks , 2018, ArXiv.

[16]  Nicholas G. Polson,et al.  Deep Learning in Finance , 2016, ArXiv.

[17]  Johannes Gehrke,et al.  Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission , 2015, KDD.

[18]  J. Teichmann,et al.  Deep hedging , 2018, Quantitative Finance.

[19]  Kenneth W. Bauer,et al.  Feature saliency measures , 1997 .