Case Studies

Zoral DE/ML Robo-Underwriting

May 18, 2020
Intelligent automation of SME loan underwriting

Results

  • 84% decrease in manual underwriting
  • 68% decrease in write-offs
  • 123% increase in loan volume
  • 27% increase in overall portfolio profitability

Automation has the potential to bring four main benefits:

The following case study explains how this was achieved for a major, North American, SME lender by using Zoral DE and Zoral ML.

The client and the problem

The client is a leading North American SME finance company. Their objective was to grow substantially their SME loan portfolio and market share. This presented a challenge. Their current underwriting processes were sophisticated and effective. However, they were traditional, manually intensive and difficult to scale.

Also, as SME lending and underwriting required substantial analytical knowledge and experience, underwriting performance was not consistent across the underwriter team.

Manual underwriting and quality control processes were supported by a set of loosely integrated systems. These, in turn, used manual information capture and semi-manual work flows.

Lack of underwriting automation caused an increase in time to process loans as the SME lender business tried to scale.

The effect of growing volumes, without systematic underwriting automation, started to impact and reduce decision quality and consistency.

The client had rapidly expanded the underwriting team to try and cope. However, this led to deteriorating portfolio results. It became clear that the underwriting process was a bottleneck and needed to be automated.

The requirement

Underwriting bottleneck

To solve the above problems the client needed to,

The solution chosen was Zoral DE / Zoral ML robo-underwriting platform. This was used to implement intelligent underwriting automation. In turn, this also helped to accelerate moving off-line products to digital.

Zoral software used

Zoral decision engineZoral DE
Zoral model libraryZoral ML
Zoral analytical data workbenchZoral ADW

Implementation Approach

The implementation approach was based on using standard Zoral DE and Zoral ML products and Zoral‘s Minimum Viable Product (MVP) implementation methodology. Implementation was completed in 15 weeks, including phased integration to client systems and 3rd party data sources, deployment to production, handover and systems training.

Zoral Decision Engine was configured to integrate with:

Zoral ML intelligent, robo-underwriter workflow was tuned and optimized for maximum effect. This was done using automatically enriched, predictive SME data.

Decision engine, SME automated underwriting

A range of Zoral ML standard models were used.

The use of Social Data, Zoral ML Social Score, and Zoral DE intelligent workflows as part of the SME Finance company system architecture is shown below.

Use of Social Data, ZML Social Score, and ZDE intelligent workflows

Default and Write-off prediction

Zoral ML default model was used to predict write-offs automatically.

ZML default score ability to rank SME loans according to probability of write-off

Note: each segment represents 10% of the SME lending portfolio population.

Initially, only raw, existing data was used to benchmark the internal underwriting score against Zoral ML default score. Additional data sources were added subsequently. This resulted in immediate improvements in overall accuracy, as can be seen below.

ZML default score vs Company internal underwriting score

Note: Zoral Platform shows higher predictive power as compared to client’s internal default prediction model. This is largely due to three factors: (1) ADW allowed a far wider range or predictive data to be discovered (e.g. 100’s of data points as input vs. client’s existing, human tuned models, which used less then 30 input variables) (2) Zoral DE used, multiple ensemble, non-linear models vs. the client’s traditional, linear model techniques (3) Zoral ML ADW contained many hundred’s of man years R&D and global experience and embedded knowledge.

The client’s data was enriched automatically using predictive social data and Zoral Social Score.

This improved write-off prediction as shown in the graph below.

Use of ZML Social Score to boost write-off prediction performance

Next, underwriting department performance was analyzed, using Zoral DE and Zoral ML default models,

Sample underwriters performance

Note: A representative sample of the clients SME loan underwriting department performance over latest one year period is shown. The blue line shows the average default rate of approved SME loans by each underwriter in the sample. Underwriters operated using the same underwriting policies, and approval procedures, however, the average default rates and corresponding write-off rates (shown in red) varied widely.

As can be seen on the graph above, the performance/metrics of the best underwriters was good, but overall performance was not consistent across the team, as shown below.

Sample underwriters KPIs

Note: Most productive underwriter #6, (who was given mostly $20,000 - $50,000 SME loans to review and underwrite), approved, on the average, 67 loans per month. The least productive and very experienced underwriter #5, on similar types of loans, approved on the average 24 loans per month but with a much lower write-off.

There were other variations in SME loan write-off performance by underwriter. These were caused by the underwriters using their internally calculated score as a starting point and then adding their own expert judgment across the five C’s of credit, (character, capacity, capital, collateral, and conditions). Using this process, they arrived at an adjusted classification of SME loan risk.

A comparison was run, using Zoral DE and Zoral ML, of underwriter collective classification of SME lending risk. This was compared to an automated Zoral DE / Zoral ML default score based classification of the same risks for a period of a year. This revealed further performance deterioration as shown below.

ZML default score vs underwriters classification

Despite variations in underwriter performance shown, the overall portfolio write-off and profitability performance was acceptable for a “steady state” business. However, this did not support the growth being experienced and anticipated. Put simply, the client’s underwriting processes and systems could not scale rapidly or safely. A larger proportion of underwriting decisions needed to be automated and better use made of a wider range of predictive customer and 3rd party data.

Next steps

A larger range of Zoral ML models and automated SME verifications were introduced. Their results were used as inputs into Zoral DE robo-underwriter to support automated and semi-automated underwriting procedures. Zoral ML robo-underwriter outputs were then integrated via Zoral DE to the client’s existing systems to provide automated underwriting decisioning. These covered the entire system lifecycle, from lead arrival through to underwriting approval and loan fulfillment. The results were,

The client was able to transition from traditional to artificial intelligence and machine learning underwriting for the majority of its portfolio.

Sample underwriters KPIs before and after ZDE automation

Robo-underwriter automation achieved with the use of Zoral DE and Zoral ML models. The SME loan portfolio write-off rate decreased. Write-off rate variations, leveraging the Zoral ML robo-underwriter, shown in grey, were significantly reduced, resulting in the “weaker” underwriter’s performance rising with increased monthly loan volumes.

Results

The results achieved are summarized below: