Digital lending is a crucial enterprise enabler for banks and monetary establishments. Prospects apply for a mortgage on-line after finishing the know your buyer (KYC) course of. A typical digital lending course of entails varied actions, reminiscent of person onboarding (together with steps to confirm the person by means of KYC), credit score verification, danger verification, credit score underwriting, and mortgage sanctioning. Presently, a few of these actions are completed manually, resulting in delays in mortgage sanctioning and impacting the shopper expertise.
In India, the KYC verification often entails id verification by means of identification paperwork for Indian residents, reminiscent of a PAN card or Aadhar card, tackle verification, and revenue verification. Credit score checks in India are usually completed utilizing the PAN variety of a buyer. The best method to tackle these challenges is to automate them to the extent attainable.
The digital lending resolution primarily wants orchestration of a sequence of steps and different options reminiscent of pure language understanding, picture evaluation, real-time credit score checks, and notifications. You’ll be able to seamlessly construct automation round these options utilizing Amazon Bedrock Brokers. Amazon Bedrock is a completely managed service that gives a alternative of high-performing basis fashions (FMs) from main AI corporations reminiscent of AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon by means of a single API, together with a broad set of capabilities to construct generative AI purposes with safety, privateness, and accountable AI. With Amazon Bedrock Brokers, you possibly can orchestrate multi-step processes and combine with enterprise information utilizing pure language directions.
On this publish, we suggest an answer utilizing DigitalDhan, a generative AI-based resolution to automate buyer onboarding and digital lending. The proposed resolution makes use of Amazon Bedrock Brokers to automate providers associated to KYC verification, credit score and danger evaluation, and notification. Monetary establishments can use this resolution to assist automate the shopper onboarding, KYC verification, credit score decisioning, credit score underwriting, and notification processes. This publish demonstrates how one can acquire a aggressive benefit utilizing Amazon Bedrock Brokers based mostly automation of a fancy enterprise course of.
Why generative AI is greatest fitted to assistants that assist buyer journeys
Conventional AI assistants that use rules-based navigation or pure language processing (NLP) based mostly steerage fall brief when dealing with the nuances of complicated human conversations. For example, in a real-world buyer dialog, the shopper may present insufficient data (for instance, lacking paperwork), ask random or unrelated questions that aren’t a part of the predefined movement (for instance, asking for mortgage pre-payment choices whereas verifying the id paperwork), pure language inputs (reminiscent of utilizing varied foreign money modes, reminiscent of representing twenty thousand as “20K” or “20000” or “20,000”). Moreover, rules-based assistants don’t present further reasoning and explanations (reminiscent of why a mortgage was denied). A few of the inflexible and linear flow-related guidelines both pressure prospects to begin the method over once more or the dialog requires human help.
Generative AI assistants excel at dealing with these challenges. With well-crafted directions and prompts, a generative AI-based assistant can ask for lacking particulars, converse in human-like language, and deal with errors gracefully whereas explaining the reasoning for his or her actions when required. You’ll be able to add guardrails to guarantee that these assistants don’t deviate from the primary matter and supply versatile navigation choices that account for real-world complexities. Context-aware assistants additionally improve buyer engagement by flexibly responding to the assorted off-the-flow buyer queries.
Answer overview
DigitalDhan, the proposed digital lending resolution, is powered by Amazon Bedrock Brokers. They’ve developed an answer that totally automates the shopper onboarding, KYC verification, and credit score underwriting course of. The DigitalDhan service gives the next options:
- Prospects can perceive the step-by-step mortgage course of and the paperwork required by means of the answer
- Prospects can add KYC paperwork reminiscent of PAN and Aadhar, which DigitalDhan verifies by means of automated workflows
- DigitalDhan totally automates the credit score underwriting and mortgage utility course of
- DigitalDhan notifies the shopper concerning the mortgage utility by means of e-mail
We have now modeled the digital lending course of near a real-world state of affairs. The high-level steps of the DigitalDhan resolution are proven within the following determine.
The important thing enterprise course of steps are:
- The mortgage applicant initiates the mortgage utility movement by accessing the DigitalDhan resolution.
- The mortgage applicant begins the mortgage utility journey. Pattern prompts for the mortgage utility embody:
- “What’s the course of to use for mortgage?”
- “I wish to apply for mortgage.”
- “My title is Adarsh Kumar. PAN is ABCD1234 and e-mail is john_doe@instance.org. I want a mortgage for 150000.”
- The applicant uploads their PAN card.
- The applicant uploads their Aadhar card.
- The DigitalDhan processes every of the pure language prompts. As a part of the doc verification course of, the answer extracts the important thing particulars from the uploaded PAN and Aadhar playing cards reminiscent of title, tackle, date of delivery, and so forth. The answer then identifies whether or not the person is an current buyer utilizing the PAN.
- If the person is an current buyer, the answer will get the inner danger rating for the shopper.
- If the person is a brand new buyer, the answer will get the credit score rating based mostly on the PAN particulars.
- The answer makes use of the inner danger rating for an current buyer to verify for credit score worthiness.
- The answer makes use of the exterior credit score rating for a brand new buyer to verify for credit score worthiness.
- The credit score underwriting course of entails credit score decisioning based mostly on the credit score rating and danger rating, and calculates the ultimate mortgage quantity for the permitted buyer.
- The mortgage utility particulars together with the choice are despatched to the shopper by means of e-mail.
Technical resolution structure
The answer primarily makes use of Amazon Bedrock Brokers (to orchestrate the multi-step course of), Amazon Textract (to extract information from the PAN and Aadhar playing cards), and Amazon Comprehend (to establish the entities from the PAN and Aadhar card). The answer structure is proven within the following determine.
The important thing resolution parts of the DigitalDhan resolution structure are:
- A person begins the onboarding course of with the DigitalDhan utility. They supply varied paperwork (together with PAN and Aadhar) and a mortgage quantity as a part of the KYC
- After the paperwork are uploaded, they’re robotically processed utilizing varied synthetic intelligence and machine studying (AI/ML) providers.
- Amazon Textract is used to extract textual content data from the uploaded paperwork.
- Amazon Comprehend is used to establish entities reminiscent of PAN and Aadhar.
- The credit score underwriting movement is powered by Amazon Bedrock Brokers.
- The information base accommodates loan-related paperwork to reply to loan-related queries.
- The mortgage handler AWS Lambda perform makes use of the data within the KYC paperwork to verify the credit score rating and inner danger rating. After the credit score checks are full, the perform calculates the mortgage eligibility and processes the mortgage utility.
- The notification Lambda perform emails details about the mortgage utility to the shopper.
- The Lambda perform will be built-in with exterior credit score APIs.
- Amazon Easy E-mail Service (Amazon SES) is used to inform prospects of the standing of their mortgage utility.
- The occasions are logged utilizing Amazon CloudWatch.
Amazon Bedrock Brokers deep dive
As a result of we used Amazon Bedrock Brokers closely within the DigitalDhan resolution, let’s have a look at the general functioning of Amazon Bedrock Brokers. The movement of the assorted parts of Amazon Bedrock Brokers is proven within the following determine.
The Amazon Bedrock brokers break every activity into subtasks, decide the correct sequence, and carry out actions and information searches. The detailed steps are:
- Processing the mortgage utility is the first activity carried out by the Amazon Bedrock brokers within the DigitalDhan resolution.
- The Amazon Bedrock brokers use the person prompts, dialog historical past, information base, directions, and motion teams to orchestrate the sequence of steps associated to mortgage processing. The Amazon Bedrock agent takes pure language prompts as inputs. The next are the directions given to the agent:
- We configured the agent preprocessing and orchestration directions to validate and carry out the steps in a predefined sequence. The few-shot examples specified through the agent directions enhance the accuracy of the agent efficiency. Primarily based on the directions and the API descriptions, the Amazon Bedrock agent creates a logical sequence of steps to finish an motion. Within the DigitalDhan instance, directions are specified such that the Amazon Bedrock agent creates the next sequence:
- Greet the shopper.
- Acquire the shopper’s title, e-mail, PAN, and mortgage quantity.
- Ask for the PAN card and Aadhar card to learn and confirm the PAN and Aadhar quantity.
- Categorize the shopper as an current or new buyer based mostly on the verified PAN.
- For an current buyer, calculate the shopper inner danger rating.
- For a brand new buyer, get the exterior credit score rating.
- Use the inner danger rating (for current prospects) or credit score rating (for exterior prospects) for credit score underwriting. If the inner danger rating is lower than 300 or if the credit score rating is greater than 700, sanction the mortgage quantity.
- E-mail the credit score resolution to the shopper’s e-mail tackle.
- Motion teams outline the APIs for performing actions reminiscent of creating the mortgage, checking the person, fetching the danger rating, and so forth. We described every of the APIs within the OpenAPI schema, which the agent makes use of to pick out probably the most applicable API to carry out the motion. Lambda is related to the motion group. The next code is an instance of the
create_loan
API. The Amazon Bedrock agent makes use of the outline for thecreate_loan
API whereas performing the motion. The API schema additionally specifiescustomerName
,tackle
,loanAmt
,PAN
, andriskScore
as required parts for the APIs. Due to this fact, the corresponding APIs learn the PAN quantity for the shopper (verify_pan_card
API), calculate the danger rating for the shopper (fetch_risk_score
API), and establish the shopper’s title and tackle (verify_aadhar_card
API) earlier than calling thecreate_loan
API.