![isq](https://www.coforge.com/hs-fs/hubfs/Imported%20sitepage%20images/isq.jpg?width=471&height=558&name=isq.jpg)
THE FACTS
Underwriters are no longer just responsible for risk selection and pricing, they are now expected to:
- Support Sales function and increase new business
- Significantly decrease the loss ratio
- Increase retention rates of existing customer base
The information used by underwriters can vary widely. Also, underwriting actions are not always truly risk-based, but instead influenced by:
- Market dynamics
- Subjective decision making
- External competition
Other Challenges
- Uniqueness of applicant’s data from a risk assessment standpoint
- Inefficiencies while handling huge datasets related to risk proles
- Risk selection and competitive pricing to avoid under/over pricing
- Deciding between risk averseness and applicant’s propensity to buy
ANALYST VIEW
Augmenting Underwriting with AI/ML
Of respondents believe that predictive model solutions are amongst the top 3 technological investments for underwriting
Machine Learning is extensively used across the Insurance value chain
![isq2-1](https://www.coforge.com/hs-fs/hubfs/Imported%20sitepage%20images/isq2-1.jpg?width=251&height=353&name=isq2-1.jpg)
Data-driven AI/ML based policy pricing and risk selection help control the Loss Ratio and contribute to Underwriting excellence
![isq3-1](https://www.coforge.com/hs-fs/hubfs/Imported%20sitepage%20images/isq3-1.jpg?width=248&height=292&name=isq3-1.jpg)
INTRODUCING SMART QUOTE, POWERED BY PEGA AI
BUSINESS PROBLEM
It is widely acknowledged within the Insurance industry that data-driven analytics based human judgment would help minimize the subjectivity in Underwriting decisions and significantly improve business efficiency
![isq4-1](https://www.coforge.com/hs-fs/hubfs/Imported%20sitepage%20images/isq4-1.jpg?width=536&height=247&name=isq4-1.jpg)
Future State/ Strategic Benefits
- Higher hit-ratio, lower loss-ratio with a more mature and self-learned predictive model
- Improved CSAT scores with possibility of offering new and highly relevant product mixes
Differentiators
- Pega predictive and adaptive modeling covering the real-time aspects of business
- Providing a holistic risk assessment of the act to aid better business decisions
Solution Overview
Powered by Pega AI/ML based decisioning models, Smart Quote will augment the Underwriting process by:
- Providing real-time quote acceptance propensity
- Underwriter decision feedback loops into the predictive model
- Customer risk data from D&B and Pitney Bowes
- Data driven Pega Predictive models
ADOPTION OF SMART QUOTE
Scope of Activities
Duration for Discovery (1 week) and Dev: 4 - 5 weeks
- Understanding of AS-IS workflow and business use case
- Extract historic data and create the prediction model
- Create the Pega Decision Strategy and link to data model
- Link Decision Strategy to Underwriter workflow
- Creation of Underwriter UI components
SIT/UAT/Go-Live: Along with next release of the Underwriting application
Team: 1 Business Analyst, 1 Pega Developer, 1 Data Analyst
Pre-requisites
- Pega 7.x or 8.x platform license, Pega Decisioning license
- Datasets with good Data Quality and Quantity of data of at least 1 - 2 years
- Unbiased data which is representative and balanced
Commercials
- Smart Quote framework provided free of charge
- 4-6 week framework customization cost to be provided to the customer as part of consultation process