Featured Product

    BoE Paper Examines Explainability of Machine Learning in Finance

    August 09, 2019

    BoE published a working paper that examines the explainability of machine learning in finance through an application to default risk analysis. Machine-learning-based predictive techniques are seeing increased adoption in a number of domains, including finance. However, due to their complexity, their predictions are often difficult to explain and validate. This is sometimes referred to as machine learning’s "black box" problem. The paper studies a machine learning model to predict mortgage defaults and proposes a framework for addressing the "black box" problem present in some machine learning applications.

    The paper addresses the explainability problem of artificial intelligence by studying the inputs and the outputs of a machine learning model.The approach is implemented by using the Quantitative Input Influence (QII) method of Datta et al (2016) in a real‑world example: a machine learning model to predict mortgage defaults. This method investigates the inputs and outputs of the model, but not its inner workings. It measures feature influences by intervening on inputs and estimating their Shapley values, representing the features’ average marginal contributions over all possible feature combinations. This method estimates key drivers of mortgage defaults such as the loan‑to‑value ratio and current interest rate, which are in line with the findings of the economics and finance literature. However, given the non‑linearity of machine learning model, explanations vary significantly for different groups of loans. The study uses clustering methods to arrive at groups of explanations for different areas of the input space. Finally, the authors conduct simulations on data that the model has not been trained or tested on. The main contribution is to develop a systematic analytical framework that could be used for approaching explainability questions in real world financial applications. The study concludes that notable model uncertainties do remain and stakeholders ought to be aware of these uncertainties.

    The paper highlights regulators as one category of stakeholders that might be interested in the workings of machine learning model of mortgage defaults of a bank to assess the riskiness of its loan book. A regulator could usefully consider an influence-based explainability approach implemented by the bank. The paper also highlights that, in such situations, it is still difficult to estimate how a complex model would behave out of sample, for instance, in stress-test scenarios where inputs are deliberately stretched. The paper shows that explainable artificial intelligence tools are an important addition to the data science toolkit, as they allow for better quality assurance of black box machine learning models. These tools can usefully complement other aspects of quality assurance, including various ways of model performance testing, understanding the properties of the data set and domain knowledge.

     

    Related Link: Working Paper

    Keywords: Europe, UK, Banking, Credit Risk, Machine Learning, Artificial Intelligence, Regtech, Model Explainability, Mortgage Default, BoE

    Related Articles
    News

    SEC Finalizes Capital and Margin Requirements for Security-Based Swaps

    SEC adopted a package of rules and rule amendments to establish capital, margin, and segregation requirements for security-based swaps, under Title VII of the Dodd-Frank Act.

    August 22, 2019 WebPage Regulatory News
    News

    ECB Revises Prudential Provisioning Expectations for New NPEs

    ECB is revising its supervisory expectations for prudential provisioning of new non-performing exposures (NPEs) specified in the “Addendum to the ECB Guidance to banks on non-performing loans” (Addendum)

    August 22, 2019 WebPage Regulatory News
    News

    CFTC Proposes to Revise Information Collection on Margin Requirements

    CFTC is requesting comments on the burdens associated with certain aspects of the Margin Requirements for Uncleared Swaps for Swap Dealers and Major Swap Participants (final rule).

    August 21, 2019 WebPage Regulatory News
    News

    FASB to Delay Effective Date for Insurance Contracts Standard

    FASB issued a proposed Accounting Standards Update that would grant all insurance companies that issue long-duration contracts, such as life insurance and annuities, additional time to apply the standard that addresses this area of financial reporting.

    August 21, 2019 WebPage Regulatory News
    News

    EBA Publishes Phase 2 of Technical Package on Reporting Framework 2.9

    EBA published phase 2 of its technical package on the reporting framework 2.9, which includes validation rules, Data Point Model (DPM) data dictionary, and XBRL taxonomies.

    August 21, 2019 WebPage Regulatory News
    News

    FSB Publishes Responses to Its Consultation Related to SME Financing

    FSB published responses received to the consultation on a report on the evaluation of the effects of financial regulatory reforms on small and medium-sized enterprise (SME) financing.

    August 21, 2019 WebPage Regulatory News
    News

    APRA Revises Related Entities Standard for Banks

    APRA published a strengthened prudential standard APS 222 on associations with related entities, with the aim to mitigate contagion risk within banking groups.

    August 20, 2019 WebPage Regulatory News
    News

    EBA and ESMA Issue Joint Response to EC Letter on Crypto-Assets

    EBA and ESMA issued a joint response to the EC letter, from July 19, 2019, on crypto-assets.

    August 20, 2019 WebPage Regulatory News
    News

    FSB on Responses to Consultation on Wind-Down of Trading Portfolios

    FSB published responses received to the consultation on the solvent wind-down of the derivatives and trading book portfolio of a global systemically important bank (G-SIB).

    August 19, 2019 WebPage Regulatory News
    News

    FSB Publishes Responses to Consultation on Resolvability Disclosures

    FSB published responses received to the consultation on disclosures for resolution planning and resolvability of banks.

    August 19, 2019 WebPage Regulatory News
    RESULTS 1 - 10 OF 3681