Towards Refined Classifications Driven by SHAP Explanations

in Holzinger, Andreas; Kieseberg, Peter; Tjoa, A. Min (Eds.) et al Machine Learning and Knowledge Extraction (2022, August 11)

Machine Learning (ML) models are inherently approximate; as a result, the predictions of an ML model can be wrong. In applications where errors can jeopardize a company's reputation, human experts often ... [more ▼]

Machine Learning (ML) models are inherently approximate; as a result, the predictions of an ML model can be wrong. In applications where errors can jeopardize a company's reputation, human experts often have to manually check the alarms raised by the ML models by hand, as wrong or delayed decisions can have a significant business impact. These experts often use interpretable ML tools for the verification of predictions. However, post-prediction verification is also costly. In this paper, we hypothesize that the outputs of interpretable ML tools, such as SHAP explanations, can be exploited by machine learning techniques to improve classifier performance. By doing so, the cost of the post-prediction analysis can be reduced. To confirm our intuition, we conduct several experiments where we use SHAP explanations directly as new features. In particular, by considering nine datasets, we first compare the performance of these "SHAP features" against traditional "base features" on binary classification tasks. Then, we add a second-step classifier relying on SHAP features, with the goal of reducing false-positive and false-negative results of typical classifiers. We show that SHAP explanations used as SHAP features can help to improve classification performance, especially for false-negative reduction. [less ▲]

On the Suitability of SHAP Explanations for Refining Classifications

in In Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART 2022) (2022, February)

In industrial contexts, when an ML model classifies a sample as positive, it raises an alarm, which is subsequently sent to human analysts for verification. Reducing the number of false alarms upstream in ... [more ▼]

In industrial contexts, when an ML model classifies a sample as positive, it raises an alarm, which is subsequently sent to human analysts for verification. Reducing the number of false alarms upstream in an ML pipeline is paramount to reduce the workload of experts while increasing customers’ trust. Increasingly, SHAP Explanations are leveraged to facilitate manual analysis. Because they have been shown to be useful to human analysts in the detection of false positives, we postulate that SHAP Explanations may provide a means to automate false-positive reduction. To confirm our intuition, we evaluate clustering and rules detection metrics with ground truth labels to understand the utility of SHAP Explanations to discriminate false positives from true positives. We show that SHAP Explanations are indeed relevant in discriminating samples and are a relevant candidate to automate ML tasks and help to detect and reduce false-positive results. [less ▲]

Transfer learning for credit card fraud detection : A journey from research to production.

in The Proceedings of the Data Science and Advanced Analytics (DSAA 2021) IEEE conference (2021)

The dark face of digital commerce generalization is the increase of fraud attempts. To prevent any type of attacks, state-of-the-art fraud detection systems are now embedding Machine Learning (ML) modules ... [more ▼]

The dark face of digital commerce generalization is the increase of fraud attempts. To prevent any type of attacks, state-of-the-art fraud detection systems are now embedding Machine Learning (ML) modules. The conception of such modules is only communicated at the level of research and papers mostly focus on results for isolated benchmark datasets and metrics. But research is only a part of the journey, preceded by the right formulation of the business problem and collection of data, and followed by a practical integration. In this paper, we give a wider vision of the process, on a case study of transfer learning for fraud detection, from business to research, and back to business. [less ▲]

Incremental learning strategies for credit cards fraud detection.

in nternational Journal of Data Science and Analytics (2021)

very second, thousands of credit or debit card transactions are processed in financial institutions. This extensive amount of data and its sequential nature make the problem of fraud detection ... [more ▼]

very second, thousands of credit or debit card transactions are processed in financial institutions. This extensive amount of data and its sequential nature make the problem of fraud detection particularly challenging. Most analytical strategies used in production are still based on batch learning, which is inadequate for two reasons: Models quickly become outdated and require sensitive data storage. The evolving nature of bank fraud enshrines the importance of having up-to-date models, and sensitive data retention makes companies vulnerable to infringements of the European General Data Protection Regulation. For these reasons, evaluating incremental learning strategies is recommended. This paper designs and evaluates incremental learning solutions for real-world fraud detection systems. The aim is to demonstrate the competitiveness of incremental learning over conventional batch approaches and, consequently, improve its accuracy employing ensemble learning, diversity and transfer learning. An experimental analysis is conducted on a full-scale case study including five months of e-commerce transactions and made available by our industry partner, Worldline. [less ▲]