Web Portal for the Consumer Finance Company
DealNet Capital, a consumer finance company, engaged DataArt to design and implement a customer-facing web portal. The new solution leveraged state-of-the-art AWS services to automate and streamline a complex and time-consuming manual document review process. As a result, DealNet significantly improved both its operational efficiency and the customer experience through the loan application journey.
About the Customer
DealNet Capital is a Canadian financial institution that leverages a unique business model of offering home renovation credit through equipment dealers, rather than lending directly to consumers.
DealNet provides homeowners and contractors with loans and leases for home improvements. The DealNet team routinely processes and verifies a massive volume of financial documents to approve the customers’ loan and lease applications. In order to be approved for a loan or a lease, a customer is required to submit funding documents (legal contracts, associated invoices, and certificates of completion once the home improvement work is finished). The documents have both handwritten and machine-typed components, which makes the validation process both incredibly challenging and time- and resource-intensive. The process of reviewing the documents and comparing them with the appropriate data from the reference dataset used to be entirely manual, which resulted in very long processing times for credit applications and unpredictable workforce headcount requirements to accommodate the market demand.
To achieve the business goal of capturing additional market share, DealNet needed to provide a quick, seamless and effective customer engagement at scale, which necessitated streamlining and accelerating the document review process.
Before initiating this project, DealNet had already used EC2 instances on AWS to run its Dealer Portal, where homeowners and contractors submit required documentation for the audit process. The optimal path forward was to keep all services on the same platform and evolve DealNet’s existing AWS infrastructure. The broad selection of available AWS services like Amazon Textract, Amazon Rekognition, Amazon SageMaker, etc. were a great fit for the main challenge facing the team, i.e. automating multi-step workflows with large numbers of repetitive manual steps.
Why the Customer Chose the Partner
DealNet’s prior relationship with DataArt as a strategic software engineering partner enjoyed a strong track record of success, thanks in large part to DataArt’s broad technology expertise, prior experience with Business Process Management systems, custom automation, and DataArt’s status as an AWS Advanced Consulting Partner.
Meeting the Challenge
The DealNet-DataArt team, in collaboration, designed and implemented the new web platform leveraging the AWS cloud. DealNet’s new Dealer Portal captures all new credit applications from consumers and dealers. The re-implemented credit approval process supported by the platform is now extremely quick. Scanning the customer’s ID populates the loan or lease application, following which the credit decision is provided from the system’s back-end in seconds. Once the application is approved, the customer submits the package of mandatory documents that require validation for compliance, lending, and financial standards to get funded. The platform leverages Amazon A2I, Amazon Textract, and Amazon Rekognition.
When funding documents are submitted for validation, they are sent to Amazon Textract to extract and identify the correct key-value pairs and OCR text. Once the values are extracted from the documents, the system compares them against the validation dataset to ensure that they are compliant.
Using the extracted key-value pairs in combination with custom logic, the system identifies the location of customers’ signatures on loan and lease agreements. The signatures are sent to Amazon Rekognition that returns a confidence score to ensure that the document is signed properly.
In cases where the extracted data does not match the expected results from the back-end system, the Amazon A2I initiates the human loop and sends data review tasks to the human staff.
The solution also provides in-depth reporting on the document validation status, numbers of documents in the queue for human review, percentage of documents reviewed with Amazon Textract, and other metrics. Based on the statistics, the management can make data-driven decisions regarding scaling the human workforce, and identify bottlenecks and areas of potential improvements in the workflow.
In order to meet key business requirements, the design of the portal leverages the following AWS services:
- Amazon Textract, a fully managed machine learning service that reads and processes any type of document, accurately extracts printed text, handwriting, forms, tables and, other data without the need for any manual effort or custom code.
- Amazon Rekognition audits the documentation whether it contains signatures.
- Amazon SageMaker (Augmented AI) is used for manual document audit. When auto audit fails, Amazon A2I creates the human loop for manual document processing.
- Amazon S3 is used to store the contracts, files for AWS Textract and AWS Rekognition, and results from AWS SageMaker.
- Amazon SQS provides communication between the web portal and the document audit workflow.
- Amazon EC2 is used to run the web portal and the document audit service.
Results and Benefits
Leveraging state of the art AWS services (Augmented AI (A2I), Amazon Textract, Amazon Rekognition) in the new solution enabled the customer to increase the productivity and speed of the document review process by up to 80%. The ability to audit the accuracy of text extraction from financial documents at scale using AI and ML services together with human workflows have also enabled DealNet to improve the quality of customer service.