Automotive SixºScore™

Model Validation & Analysis

Built on millions of records, Trust Science’s Canadian Automotive Six°Score™ provides industry-leading accuracy tailored to the non-prime auto finance market. Leveraging the Credit Bureau+™ platform, the Canadian Automotive Six°Score™ harnesses the power of machine learning and explainable artificial intelligence for unparalleled predictiveness on more applicants. Clients get vastly improved business performance, double-digit ROI, and more financially inclusive lending, backed by data-driven insights that enable you to swap out bad deals while swapping in good deals.

1

Better than the Bureaus

2

Deep Subprime Performance

3

Bottom-Line ROI

4

Augmenting Your Scores and Strategy

Better than the Bureaus

Score Overview

The Canadian Automotive Six°Score™ was built on millions of records in the Canadian subprime market, creating a highly focused and highly predictive model tailored to automotive lending and its unique considerations.

Statistical Summary

The Canadian Automotive Six°Score™ offers strong statistical performance across all predictiveness and good/bad separation metrics. The following validation was completed based on a sample of 352,000 booked subprime loans.

Kolmogorov-Smirnov (KS) Test Results

KS represents a model’s ability to differentiate good and bad populations. Six°Score™ returned a
KS result of 31.43, highlighting its power at its most predictive.

AUC-ROC Results

ROC signifies the diagnostic ability of a model. Six°Score™ returned an AUC-ROC result of 0.7127, highlighting its predictive power across its score range.

Gini & Lorenz Curve

The Lorenz curve and Gini coefficient measure a model’s ability to capture bad loans in lower score tiers. Six°Score had a Gini coefficient of 0.4258, proving its bad capture abilities.

Client-Proven: Better than the Bureaus

Trust Science prepared a validation study on all clients that ran the Canadian Automotive Six°Score™ in parallel with a conventional bureau score or re-scored past applications. Across all metrics of performance, the Six°Score™ vastly outperformed the bureau score. The test window ran on over 500,000 subprime loans booked from Q1 2022 to Q1 2023.

Statistical Lift

0 %
KS Lift

Six°Score differentiates between good and bad loans with significantly greater accuracy vs. a common bureau score.

0 %
Gini Lift

Six°Score rank orders better, capturing more bad loans in low score bands vs. a common bureau score.

0 %
ROC Lift

Six°Score has overall superior good and bad classification, with less error vs. a common bureau score.

Better Bad Capture Rates

By capturing more bad loans in lower score bands, Six°Score helps increase approvals with lower risk.

Deep Subprime Population Comparison

While the bureau score had minimal differentiation power between good and bad loans, Trust Science offered successful risk rank-ordering even in this tier by providing a 360° view of the consumer. Six°Score™ enables you to approve more underserved borrowers in this range with confidence. Six°Score™ vastly outperformed the bureau score with:

0 %
KS Lift
0 .0%
Gini Lift
0 %
ROC Lift

Helping Lenders Approve More Loans

By providing a more comprehensive view of the consumer’s risk, Trust Science helps lenders better identify good and bad credit risks. Through swapping in better borrowers and swapping out poor performers, clients approve more loans while retaining a consistent (or lower) default rate.

For a client with a target default rate of 4%, Six°Score helped the lender approve 79.52% more loans. With an additional rules overlay powered byFl°wBuilder, Trust Science helped the lender optimize return on equity by further reducing default rates while retaining over 30% more approvals.

Helping Lenders Get Better Performance & ROE

Six°Score can also vastly improve performance by reducing defaults without “tightening” the credit box, allowing lenders to retain similar approvals while observing vast improvements to default rates and return on equity.

For a client with a target approval rate of 60%, Six°Score helped the lender lower default rates by 27.76%, which translated to a 5.15% increase in net earnings and a 4.98% increase in return on equity.

Augment Your Scores and Strategies

Six°Score works with your existing scores and strategies to provide an intelligent orthogonal view to approve more consumers, reduce defaults, and improve ROE.

Default Rate Matrix

SixºScore reveals Invisible Prime™ borrowers missed by conventional bureaus, & correctly identifies bad borrowers that would typically otherwise be approved by the bureaus.

Distribution Matrix

Six°Score™ is able to identify significant swap sets providing material opportunities to boost return on assets and improve overall portfolio performance.

Helping Lenders Approve More Loans

A lender originally approved the top 40% of bureau scores (the rightmost two columns), observing a default rate of 4.25%. However, the lender also leaves out a tranche of borrowers that Six°Score correctly identifies as better performers than the existing book. By applying Six°Score as a second-look approval on these declines, this lender got a higher ROE with:
0 %
More Earnings
0 %
Lower Bad Rate
0 %
More Approvals

Lowering Risk: Intelligent Tightening

A lender originally approved the top 40% of bureau scores (the rightmost two columns), observing a default rate of 4.25%. Seeking to reduce defaults, Six°Score helped the lender intelligently decline its worstperforming borrowers. By applying Six°Score to decline the bottom 40% of its approvals, this lender received excellent results just 18% less approvals:
0 %
Less Bad Loans
0 %
Lower Bad Rate
0 .0%
Higher ROE