WE LIKE SOLVING
THE HARD PROBLEMS!

Deep Future Analytics (DFA) is the result of 30 years of research and experience in credit risk analytics, in all its many aspects. With a team of 25 expert data scientists, technologists, and economists, DFA is led by Dr. Joseph Breeden, a pioneer in the field of risk modeling. Together, we equip financial institutions with actionable intelligence to drive smarter, more strategic decisions.

MRM: AI Monitor

Credit Risk
Software Solutions

Consulting Services

Revolutionizing Consumer Risk Analytics

First-in-Industry Innovations

1st

to invent vintage modeling for consumer lending in the 1990s

1st

major CECL study released in April 2017

1st

solution that integrates all credit risk needs with the same account-level, scenario-driven modeling framework.

1st

to deploy stress testing software, 10 years before CCAR / DFAST

1st

to deploy CECL software, 1 week after the rules were finalized

1st

to solve economic contagion modeling for climate risk

1st

to deploy AI compliance monitoring for frontline AI

Pioneering Solutions

Our software predicted the US mortgage crisis as early as Feb 2006 for our clients.
Solved the long-range forecasting problem in machine learning and AI
Solved the out-of-time deterioration problem in scoring, traditional and ML/AI

Credit Risk Software Solutions

Retail Portfolio Analytics

including delinquency, loss, and profitability; vintage-based analysis and forecasting; through-the-door distribution shifts; pricing sensitivity

Stress Testing

for Retail Portfolios (Personal Loans, Cards, Auto, Mortgages, Small Business Loans)

IFRS 9 & CECL

credit risk modeling for transparent financial reporting.

Yield Forecasting

including credit loss, yield, and NPV for smarter capital allocation.

Pricing Optimization

for Risk-based pricing and Cut-off score optimization to balance risk, returns, and growth

APR and Adverse
Selection Benchmarking

for all loan types to aid in competitive analysis and loan origination strategy

Adverse Selection
Early Warning / Opportunity

A panel-based Origination Score connects directly to PD through the lifecycle

Coming Soon

Consulting Services

Advanced Credit Score Development

Portfolio Valuations/ Asset Valuations

Climate Risk

Creditline
Optimization

Yield & Profitability Modeling

DFA Consulting Success Stories

Machine learning models for Personal Loans and Cards for the largest FinTech lender in the US

Climate risk stress testing for major US GSEs & training for ECB

Auto loan asset valuation for several top-tier US PrivateEquity firms

Asset valuation for US banks/ FinTechs for buying loan portfolios

Stress testing for several global lenders

Risk-based pricing and benchmarking project for a top auto lender in the US

What Sets DFA Apart

Adverse Selection Insights

Quantified and seamlessly integrated into forecasts for smarter risk management.

Robust, Reliable Models

No overfitting in machine learning and logistic regression, ensuring accurate predictions.

True Portfolio Optimization

Supports true product and portfolio optimization over time for sustained growth.

Data-Driven Optimization

Cut-off scores and pricing fine-tuned to yield thresholds—no guesswork, just precision.

Advanced Stress Testing

Traditional macroeconomic and climate risk stress tests applied down to the account level.

AI-Driven Strategy

Empowers Strategic Recommendation Agents (SRA), the AI that businesses need.

DFA Technology

Deployment Modes

On-Premises

SAS, R, Python
Library license
Outputs to Tableau,
PowerBI, Other

Cloud

AWS-Hosted Software
DFA-maintained models
Interactive UI

Solutions are licensed by modules.

Articles

Solving the Long-Range Forecasting Problem in Supervised Learning

In a world where big data is everywhere, no one has big data relative to the economic cycle.

10/Jul/2025 07:00 PM
Creating Unbiased Machine Learning Models by Design

Unintended bias against protected groups has become a key obstacle to the widespread adoption of machine learning methods

10/Jul/2025 07:00 PM
Stress Testing for Pandemics

Given the unfortunate global headlines about coronavirus, lenders are starting to ask about stress testing the financial impacts of possible pandemics. For some, that is dusting off old plans. For others, it is devising new plans. For myself, it is reliving the past.

10/Jul/2025 07:00 PM
Normalizing Pandemic Data for Credit Scoring

The COVID-19 pandemic created abnormal credit risk conditions that did not align well with pre-2020 credit scores. Since the pandemic, most organizations have either excluded the period 2020-2021 from their modeling or included it without adjustment, leaving it as noise in the data. Model validators and examiners have been divided about requiring one of these approaches or defaulting to model developer judgment. None of this is ideal from a model development perspective. We have found that a technical solution is available. Our analysis uses lifecycle and environment outputs from an Age-Period-Cohort analysis as fixed offsets to the credit score development. Panel data is used, so the credit score is developed with a discrete time survival model approach. We tested logistic regression and stochastic gradient boosted regression trees as estimators with the panel data and APC inputs. For this research, we used Fannie Mae data. The APC model was estimated on the full available history, from 2005 through 2024. The origination scores were estimated on two-year periods from 2016 through 2024 and tested on all other periods, including a score that was developed on the full period. All models were also tested on comparably prepared data from Freddie Mac for cross-validation.

10/Jul/2025 07:00 PM
Current expected credit loss procyclicality: it depends on the model

Current expected credit loss procyclicality: it depends on the model

25/Jul/2025 07:00 PM
When Big Data Isn’t Enough: Solving the long-range forecasting problem in supervised learning

n a world where big data is everywhere, no one has big data relative to the economic cycle. Data volume needs to be thought of along two dimensions. (1) How many accounts / transactions / data fields do we have? (2) How much time history do we have? Few, if any, big data sets include history covering one economic cycle (back to 2005) or two economic cycles (back to 1998). Therefore, unstructured learning algorithms will be unable to distinguish between long-term macroeconomic drivers and point-in-time variations across accounts or transactions. This is the colinearity problem that is well known in consumer lending.

25/Jul/2025 07:00 PM
Consumer risk appetite, the credit cycle and the housing bubble

In this paper, we explore the role of consumer risk appetite in the initiation of credit cycles and as an early trigger of the US mortgage crisis. We analyze a panel data set of mortgages originated between 2000 and 2009 and follow their performance up to 2014. After controlling for all of the usual observable effects, we show that a strong residual vintage effect remains. This vintage effect correlates well with consumer mortgage demand, as measured by the Federal Reserve Board’s Senior Loan Officer Opinion Survey, and with changes in mortgage pricing at the time the loan was originated. Our findings are consistent with an economic environment in which the incentives of low-risk consumers to obtain a mortgage decrease when the cost of obtaining a loan rises. As a result, mortgage originators generate mortgages from a pool of consumers with changing risk profiles over the credit cycle. The unobservable component of the shift in credit risk, relative to the usual underwriting criteria, may be thought of as macroeconomic adverse selection.

25/Jul/2025 07:00 PM
CECL ASSESSING THE ALTERNATIVES

This study evaluates various models for implementing the Current Expected Credit Loss (CECL) method, using a large mortgage data set from Fannie Mae and Freddie Mac

24/Jul/2025 07:00 PM