Break through Lending Risk Assessment with an AI-Driven Approach

By Joshua Gordon

How lenders can move beyond traditional scoring and lending practices to manage risk in an increasingly uncertain environment The Clouds of Economic Uncertainty This blog post is a summary of our lending webinar, titled Risk Assessment Reinvented. Watch the webinar to gain a more comprehensive perspective. As we start to close out 2025, it’s clear that the lending market is experiencing a perfect storm. Economic headwinds and a shift in consumer behaviors are causing an increase in uncertainty, exposing lenders to vulnerabilities that, while always present, have become increasingly worrisome in traditional risk assessment models. Auto lenders, particularly those in the non-prime sector, are at the center of the turbulence. Delinquency rates are surging in unexpected segments, signaling a fundamental shift in how risk is measured and contained. Source: Federal Reserve Bank of New York, February 2025 According to the Federal Reserve Bank of New York, the fourth quarter of…

Practical Guide for Feature Engineering of Time Series Data

By Joshua Gordon

Introduction Time series modeling is one of the most impactful machine learning use cases with broad applications across industries. Traditional time series modeling techniques, such as ARIMA, often automatically incorporate the time component of the data by using lagged values of the target variable as model inputs. While these techniques provide interpretable coefficients that aid in understanding the contribution of each variable to the forecast, they can be sensitive to outliers, missing data, and changes in the underlying data-generating process over time. As a result, their accuracy may be compromised.  On the other hand, machine learning combined with feature engineering offers a more robust approach to time series modeling. This approach can handle complex, non-linear relationships and is well-suited for large relational datasets with more complex relationships and intricate interdependencies. Feature engineering plays a crucial role in time series modeling, as it involves selecting and transforming raw data into meaningful…