Explainability and Fairness in Machine Learning: Improve Fair End-to-end Lending for Kiva

Artificial Intelligence is finding its way to ever more applications. Nonetheless, it is increasingly required that decision-making procedures must be explainable and fair. As many applications are based on black-box models, there is a strong need for more explainable AI algorithms. For this reason, our paper explores the practical implications and effectiveness of four bias mitigation algorithms (learning fair representations, reweighing, Equality of Odds, and Reject Option based Classification) based on a standard XGBoost classifier to build an explainable and fair prediction model on a real-world loan dataset. The models were evaluated based on their performance, fairness, and explainability. Potential biases, i.e. fairness, were detected with the use of NLP techniques and evaluated with the AIF360 metrics, whereas the explainability of the model was tested by post-hoc explanations (SHAP method). The best results were obtained by the reweighing algorithm that improved the fairness while maintaining a high model performance and explainability.

[1]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[2]  Tom Fawcett,et al.  Data Science and its Relationship to Big Data and Data-Driven Decision Making , 2013, Big Data.

[3]  Toon Calders,et al.  Data preprocessing techniques for classification without discrimination , 2011, Knowledge and Information Systems.

[4]  Klaus-Robert Müller,et al.  Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models , 2017, ArXiv.

[5]  Rachel K. E. Bellamy,et al.  AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias , 2018, ArXiv.

[6]  Arvind Narayanan,et al.  Semantics derived automatically from language corpora contain human-like biases , 2016, Science.

[7]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[8]  Carlos Eduardo Scheidegger,et al.  Certifying and Removing Disparate Impact , 2014, KDD.

[9]  Jimeng Sun,et al.  Explainable Prediction of Medical Codes from Clinical Text , 2018, NAACL.

[10]  Juan Carlos Fernández,et al.  Multiobjective evolutionary algorithms to identify highly autocorrelated areas: the case of spatial distribution in financially compromised farms , 2014, Ann. Oper. Res..

[11]  L. Shapley.  A Value for n-person Games , 1988 .

[12]  Kush R. Varshney,et al.  Optimized Data Pre-Processing for Discrimination Prevention , 2017, ArXiv.

[13]  Alexandra Chouldechova,et al.  The Frontiers of Fairness in Machine Learning , 2018, ArXiv.

[14]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[15]  Jun Sakuma,et al.  Fairness-Aware Classifier with Prejudice Remover Regularizer , 2012, ECML/PKDD.

[16]  N. A. Diamantidis,et al.  Unsupervised stratification of cross-validation for accuracy estimation , 2000, Artif. Intell..

[17]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.

[18]  Klaus-Robert Müller,et al.  "What is relevant in a text document?": An interpretable machine learning approach , 2016, PloS one.

[19]  Krishna P. Gummadi,et al.  A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual &Group Unfairness via Inequality Indices , 2018, KDD.

[20]  Henda Hajjami Ben Ghézala,et al.  Comparative study of word embedding methods in topic segmentation , 2017, KES.

[21]  Krishna P. Gummadi,et al.  Fairness Constraints: Mechanisms for Fair Classification , 2015, AISTATS.

[22]  Xin Rong,et al.  word2vec Parameter Learning Explained , 2014, ArXiv.

[23]  Seth Neel,et al.  Rawlsian Fairness for Machine Learning , 2016, ArXiv.

[24]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.

[25]  Shahzad Qaiser,et al.  Text Mining: Use of TF-IDF to Examine the Relevance of Words to Documents , 2018, International Journal of Computer Applications.

[26]  Xiangliang Zhang,et al.  Decision Theory for Discrimination-Aware Classification , 2012, 2012 IEEE 12th International Conference on Data Mining.

[27]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[28]  Chris H. Q. Ding,et al.  K-means clustering via principal component analysis , 2004, ICML.

[29]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.