Using real time anonymized data from private companies, this paper focuses on the ripple effects of a sharp decrease in spending by high-income households on both small businesses and low-income workers.

This article charts how FinTech companies are deploying new technology pilot programs to aid in COVID recovery. The article references several companies deploying big data analysis capabilities and notes uses of distributed ledgers for settling trades.

This brief from the World Economic Forum evaluates how the use of personal data – and business models for monetizing that data – might evolve as firms respond to the pandemic. For example, machine learning algorithms previously deployed to analyze consumer tastes could be deployed to track viral detection.

This article analyzes the technical nuances and legal implications of using synthetic data, which uses machine learning techniques to modify raw data, as an alternative to anonymization or differential privacy to protect privacy interests while facilitating research.

This paper surveys several existing federal laws bearing on management of financial data as well as recent state activity before analyzing potential elements for comprehensive federal legislation.

This research paper analyzed whether unstructured digital data can substitute for traditional credit bureau scores with an analysis of loan-level data from a large Indian fintech firm. The researchers found that evaluating creditworthiness based on social and mobile footprints can potentially expand credit access. Variables found to significantly improve default prediction and outperform credit bureau scores include the number and types of apps installed, metrics of the applicant’s social connectivity, and measures of borrowers’ “deep social footprints” derived from call logs.

This report analyzes mortgage default using information taken from the JPMorgan Chase Institute housing finance research to evaluate the relationship between liquidity, equity, income level, and payment burden and default. Across all four groups, the report finds that liquidity may be more predictive for determining the likelihood of mortgage default particularly among borrowers with little post-closing liquidity and little liquidity but high equity. Overall, the report determines that alternative underwriting standards incorporating a minimum amount of post-closing liquidity may be a more effective way to prevent mortgage default compared to using DTI thresholds at origination.

This essay discusses the legal requirements of pricing credit and the architecture of machine learning and intelligent algorithms to provide an overview of legislative gaps, legal solutions, and a framework for testing discrimination that evaluates algorithmic pricing rules. Using real-world mortgage data, the authors find that restricting the data characteristics within the algorithm can increase pricing gaps while having a limited impact on disparity.

This paper examines geographic patterns to assess the extent to which where one resides is correlated with one’s likelihood of remaining credit invisible. The paper explores the following topics: credit deserts, credit invisibility in rural and urban areas, entry products by geography, and credit invisibility. The Bureau of Consumer Financial Protection’s Office of Research

This paper evaluates users’ digital footprints or the information that people leave online by accessing or registering a website to predict consumers’ likelihood of default. Using more than 250,000 observations, the authors show that information gleaned from people’s digital footprint can be equal to or even exceed the information content of credit bureau scores. FDIC Center for Financial Research Working Paper No. 2018-04