". . .the overarching framework of data splitting, feature selection, model tuning, and overall assessment is statistically sound."

Today, the majority of lenders leverage the scoring system offered by their national credit reporting agencies (CRAs) or bureaus as part of the creditworthiness assessment of borrowers. However, the availability of data is limited to applicants with an existing credit history, usually those in the middle to upper-income segments.

FinTechs such as CredoLab leverage a very particular type of alternative data – smartphone metadata – to generate digital behavioural scorecards that reduce the reliance on customers having existing banking or credit history. This Whitepaper throws light on how multiple industries, all at the intersection with financial services, can improve lending decisions and enhance customer experience through machine learning-driven credit risk modelling.

Read the white paper

What's inside?

Smartphone Metadata

Find out more about the power and useability of the new frontier in credit risk.

Universal Application

Explore how the major industries across the globe are ready to adopt this technology.

Democratizing Financial Services

Discover the new face of FinTech that is shifting the focus from mere credit access to financial empowerment.

Read the white paper

". . .the overarching framework of data splitting, feature selection, model tuning, and overall assessment is statistically sound."

- Dr Xiaofei (Susan) Wang, PhD, Department of Statistics & Data Science, Yale University

Please fill in your details to get exclusive access to the e-book

Thank you! Your submission has been received and we will send you your copy shortly.

Oops! Something went wrong while submitting the form.

CredoLab is at the forefront of innovative risk management practices that engage with novel credit risk modelling approaches availed by the surge in cell phone use. Core to CredoLab’s business is its modelling pipeline. Taking the smartphone as input, the data processing pipeline consists of a series of automated steps, rooted in machine learning techniques, that ultimately outputs a predictive model for credit default. To protect the confidentiality and to ensure against bias towards individual loan customers, only non-identifying metadata is used.

This e-book reports the findings of Dr Xiaofei (Susan) Wang, Lecturer and Research Scholar, Yale University from a review she did on CredoLab’s scoring model. She considered a vast array of alternative approaches for the various different steps of the pipeline and found favourable results, including when applied to real data.

In this e-book, we first explore the data sets that CredoLab consumes, how it translates it into scores, and the outcome it serves. In the latter part of the paper, we take a look at how CredoLab’s algorithm fared when compared to that of other major players with similar scoring models.

Dr. Xiaofei (Susan) Wang, PhD

Lecturer and Research Scholar, Department of Statistics & Data Science, Yale University

Born in Nanjing, China, Dr. Wang moved to the USA at an early age and has been associated with some of the leading institutions. She did her bachelors from the University of California and her PhD in Statistics from Yale University. She currently holds esteemed positions at a number of associations and works at Yale University as a lecturer and research scholar. She has a number of publications and accolades to her credit.