Technology

Computer Vision, Neural Networks and Deep Learning
claim
OCR
NLP& Policy CHeck
enrichments
recommendations
claim
OCR
NLP& Policy CHeck
enrichments
recommendations

Optical Character Recognition

Our OCR translates all unstructured data such as handwritten medical reports and prescriptions into structured data. Once OCR extraction is complete, the data will be matched against the policy interpreted by NLP.

Natural Language Processing

One of Sprout.ai’s NLP application:

Sprout.ai generates contextual reasoning through using NLP and Knowledge Graphs. NLP is used to understand the contents of the policy document and enables us to build the rules within the policy to automatically check whether the claim is valid in regard to the policy agreement.

Policy Check

Once NLP has interpreted the policy document, our solution will then match this to the description of the claim to automatically check whether the claim is covered under the customer’s specific policy.

Enrichments example for a property claim

Enrichments

  • Sprout.ai leverages all unstructured data from a claim to acquire more information using external providers
  • We enrich ‘data sprouts’ from individual claims by up to 300%, with real-time information sourced from web-based and public data sources
  • All sources of data are acquired from GDPR compliant data providers therefore there is no risk of a data breach
  • Simultaneously checking for fraud, abuse and outliers referring to both macro and micro level data sources
  • Sprout.ai can analyse the structured data held by the insurer to provide context and recommendations
Claim Recommendation
Sprout.ai vs Human Capabilities

Claims information extracted from claim documentation provided by customer

Text Extraction

Claim details extracted and checked against the policy to see whether it is included

Policy Checking
If claim does not fit the policy, claim handlers will need to verify if a claim is covered manually by checking policy and policy attachments

Claim is checked for to see if it is related to any fraudulent activity or if the customer has a fraudulent past using APIs

Fraud Check
If possible fraud is found, claims will be manually checked based on claims handlers experience of whether this should be referred to SIU (Special Investigation Unit)
Items with missing invoices can be validated and claimed price of products are validated again with further APIs
Missing Invoices
If the price of products cannot be validated, the claim is reviewed by the supplier network who will charge the insurer to find accurate prices of claimed items
Claim Turnaround Time
Operational Costs
Fraudulent Claim Detection
Claim Approved
Text Extraction

Claims information extracted from claim documentation provided by customer

Policy Checking

Claim details extracted and checked against the policy to see whether it is included

Fraud Check

Claim is checked for to see if it is related to any fraudulent activity or if the customer has a fraudulent past using APIs

Missing Invoices
Items with missing invoices can be validated and claimed price of products is validated again with further APIs
Claim Approved
Claim Turnaround Time
Operational Costs
Fraudulent Claim Detection
If claim does not fit the policy, claim handlers will need to verify if a claim is covered manually by checking policy and policy attachments
If possible fraud is found, claims will be manually checked based on claims handlers experience of whether this should be referred to SIU (Special Investigation Unit)
If prices of items cannot be validated, the claim is reviewed by the supplier network who will charge the insurer to find accurate prices of claims items

BOOK A DEMO

We use cookies to give you the best online experience.By using our website you agree to our Cookie Policy.