Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges

Xu, Fang; Uszkoreit, Hans; Du, Yangzhou; Fan, Wei; Zhao, Dongyan; Zhu, Jun

doi:10.1007/978-3-030-32236-6_51

Cited by 401 publications

(228 citation statements)

References 10 publications

Supporting

Mentioning

224

Contrasting

Unclassified

Order By: Relevance

“…Explainable AI (XAI) refers to the process of creating AI models which use interpretable parameters as part of their decision-making process. 263 The signicance of this is enormous, starting with data protection and copyrights. As per 2018, according to General Data Protection Regulation (GDPR) citizens of EU are granted the "right to explanation" if they are affected by a decision-making algorithm.…”

Section: Future Aspectsmentioning

confidence: 99%

A review on machine learning algorithms for the ionic liquid chemical space

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Future Aspectsmentioning

confidence: 99%

A review on machine learning algorithms for the ionic liquid chemical space

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Hence, such methods could also be of great usage for social problems aiming to make accurate predictions about social or behavioral phenomena ( Emmert-Streib et al, 2018b ). Second, deep learning networks are frequently criticized for lacking interpretability and explainability ( Lipton, 2016 ; Xu et al, 2019 ; Emmert-Streib et al, 2020b ). Interestingly, this lack might be overcome by utilizing social networks underlying big social data for informing the deep network architectures.…”

Section: Discussionmentioning

confidence: 99%

Data-Driven Computational Social Network Science: Predictive and Inferential Models for Web-Enabled Scientific Discoveries

Emmert‐Streib¹,

Dehmer²

2021

Front. Big Data

View full text Add to dashboard Cite

The ultimate goal of the social sciences is to find a general social theory encompassing all aspects of social and collective phenomena. The traditional approach to this is very stringent by trying to find causal explanations and models. However, this approach has been recently criticized for preventing progress due to neglecting prediction abilities of models that support more problem-oriented approaches. The latter models would be enabled by the surge of big Web-data currently available. Interestingly, this problem cannot be overcome with methods from computational social science (CSS) alone because this field is dominated by simulation-based approaches and descriptive models. In this article, we address this issue and argue that the combination of big social data with social networks is needed for creating prediction models. We will argue that this alliance has the potential for gradually establishing a causal social theory. In order to emphasize the importance of integrating big social data with social networks, we call this approach data-driven computational social network science (DD-CSNS).

show abstract

“…Therefore, it is highly unlikely that any financial expert is ready to trust the predictions of a model without any sort of justification [4]. Model explainability has recently regained attention with the emerging area of eXplainable AI (XAI), a concept which focuses on opening black-box models in order to improve the understanding of the logic behind the predictions [5,6]. In credit scoring, lenders need to understand the model's predictions to ensure that decisions are made for the correct reasons.…”

Section: Problem Definitionmentioning

confidence: 99%

An Explanation Framework for Interpretable Credit Scoring

Demajo¹,

Vella²,

Dingli³

et al. 2021

IJAIA

View full text Add to dashboard Cite

With the recent boosted enthusiasm in Artificial Intelligence (AI) and Financial Technology (FinTech), applications such as credit scoring have gained substantial academic interest. However, despite the evergrowing achievements, the biggest obstacle in most AI systems is their lack of interpretability. This deficiency of transparency limits their application in different domains including credit scoring. Credit scoring systems help financial experts make better decisions regarding whether or not to accept a loan application so that loans with a high probability of default are not accepted. Apart from the noisy and highly imbalanced data challenges faced by such credit scoring models, recent regulations such as the `right to explanation' introduced by the General Data Protection Regulation (GDPR) and the Equal Credit Opportunity Act (ECOA) have added the need for model interpretability to ensure that algorithmic decisions are understandable and coherent. A recently introduced concept is eXplainable AI (XAI), which focuses on making black-box models more interpretable. In this work, we present a credit scoring model that is both accurate and interpretable. For classification, state-of-the-art performance on the Home Equity Line of Credit (HELOC) and Lending Club (LC) Datasets is achieved using the Extreme Gradient Boosting (XGBoost) model. The model is then further enhanced with a 360-degree explanation framework, which provides different explanations (i.e. global, local feature-based and local instance- based) that are required by different people in different situations. Evaluation through the use of functionally-grounded, application-grounded and human-grounded analysis shows that the explanations provided are simple and consistent as well as correct, effective, easy to understand, sufficiently detailed and trustworthy.

show abstract

Explainable AI: A Brief Survey on History, Research Areas, Approaches and Challenges

Cited by 401 publications

References 10 publications

A review on machine learning algorithms for the ionic liquid chemical space

A review on machine learning algorithms for the ionic liquid chemical space

Data-Driven Computational Social Network Science: Predictive and Inferential Models for Web-Enabled Scientific Discoveries

An Explanation Framework for Interpretable Credit Scoring

Contact Info

Product

Resources

About