mlsanityData to 7 Oct 2026

Harnessing value from data science in business: ensuring explainability and fairness of solutions

arXiv 2108.07714 ↗First posted 10 Aug 2021cs.CY cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The paper introduces concepts of fairness and explainability (XAI) in artificial intelligence, oriented to solve a sophisticated business problems. For fairness, the authors discuss the bias-inducing specifics, as well as relevant mitigation methods, concluding with a set of recipes for introducing fairness in data-driven organizations. Additionally, for XAI, the authors audit specific algorithms paired with demonstrational business use-cases, discuss a plethora of techniques of explanations quality quantification and provide an overview of future research avenues.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 48 of its 97 references that are in the map. First posted on arXiv 10 Aug 2021.

Builds on

48 of 97 references.

References · 48

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  10. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  11. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  12. 2019Attention is not Explanationcited by 916
36 more
  1. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  2. 2014Certifying and removing disparate impactcited by 715
  3. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  4. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  5. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  6. 2017Interpretation of Neural Networks is Fragilecited by 443
  7. 2017On Fairness and Calibrationcited by 406
  8. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  9. 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
  10. 2017The (Un)reliability of saliency methodscited by 331
  11. 2017Right for the Right Reasons: Training Differentiable Models by Constraining their Explanationscited by 293
  12. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  13. 2015The Variational Fair Autoencodercited by 223
  14. 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 212
  15. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  16. 2015Deep Kalman Filterscited by 163
  17. 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 144
  18. 2018Why Is My Classifier Discriminatory?cited by 143
  19. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  20. 2016Composing graphical models with neural networks for structured representations and fast inferencecited by 113
  21. 2018Improving DNN Robustness to Adversarial Attacks using Jacobian Regularizationcited by 88
  22. 2015The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classificationcited by 76
  23. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  24. 2017Interpretable & Explorable Approximations of Black Box Modelscited by 54
  25. 2017Towards better understanding of gradient-based attribution methods for Deep Neural Networkscited by 51
  26. 2017Deep and Confident Prediction for Time Series at Ubercited by 50
  27. 2019Measurable Counterfactual Local Explanations for Any Classifiercited by 48
  28. 2020NBDT: Neural-Backed Decision Treescited by 46
  29. 2018Improving the Interpretability of Deep Neural Networks with Knowledge Distillationcited by 37
  30. 2019Regularizing Black-box Models for Improved Interpretabilitycited by 35
  31. 2018TED: Teaching AI to Explain its Decisionscited by 33
  32. 2014Learning unbiased featurescited by 10
  33. 2018Deep Weighted Averaging Classifierscited by 9
  34. 2017Interpreting Classifiers through Attribute Interactions in Datasetscited by 8
  35. 2019Functional Transparency for Structured Data: a Game-Theoretic Approachcited by 6
  36. 2019Hybrid Predictive Model: When an Interpretable Model Collaborates with a Black-box Modelcited by 1

Built on by

Not cited yet.