Whitepaper

Author : Amit Unde

 -

Contents
1. Data Intake Problem in Commercial Insurance 03

2. Metamodel-driven Solution 04

3. Business Benefits 05

4. About the Author 05

5. About L&T Infotech 05

 Automating Data Intake Process in
Commercial Underwriting

Data Intake problem in Commercial Insurance

What is the biggest hurdle in Commercial Carriers typically have a data processing (called as
Insurance for rapidly turning around a quote prep or profiling) team that scrubs the data, puts it
request, especially for mid and large markets? It is in a consistent format, maps codes (e.g. occupancy
undoubtedly the submission data intake codes) to internal standards, enriches data with
processing. Many carriers have tackled internally available information, and then sends the
standardization of submission forms, but not that information to underwriters. This process may take
of accompanying data. multiple days to weeks, depending on the size and
quality of data.
For example, it is typical for a midsize to large
commercial property risk to include thousands of After this process is done, Underwriters conduct
locations and property types, called as Statement risk assessment, classification, pricing, and respond
of Value (SOVs). Brokers typically send it as an excel to quotes. The quality and turnaround time of
file with possibly multiple worksheets. Sometimes, underwriting process depend completely on the
loss run reports are attached (again in excel or pdf underlying data quality. As there are typically
format). They use inconsistent/free-flow format. thousands of locations, this process can be
The addresses and data may be incomplete, and expedited by appropriately flagging the risks that
need to be tagged with the information available they should pay attention to. This can also happen
in-house. during the data intake process.

Manual mapping of codes

Third party Risk

Data providers
Prep Team

Inefficient manual data Inefficient data gathering Process

Prep process – Takes -More time spent on data gathering
Multiple days before Rather than decision making
Data is Provided to
underwriters

Underwriter

Internal Data

Clearly, the turnaround time and quality can be significantly improved if the current manual process is
replaced by more automated data intake process. To summarize, the data intake process must:

Handle inconsistent input files in multiple formats Map external codes to internal codes

Improve data quality by scrubbing the data Run rules to flag the risks for underwriting
scrutiny
Enrich missing/incomplete data

L&T Infotech Proprietary 03 / 05

 Automating Data Intake Process in
Commercial Underwriting

Those who have tried to automate the process enrichment requirements. The solution needs to
know that the solution to this problem is not be - Highly configurable, Metamodel-driven, auto-
simple; due to variety of input formats, different mated with provision of manual intervention
types of data for different products and varied as required.

NO SQL
Third party / Internal
Metamodeler Services and business rules

Highly Configurable
Uses
First time mapping Uses Uses
Standardized and
Enriched Data

Importer Translator Code Mapper Enrichment

Station

Input Files
Data Processing DB Sub0DB
No SQL
Manual Intervention if required

User Interface

The heart of the solution is a Metamodel, which may require manual intervention if the code
means a model of a model. It stores the mapping rules are not defined for all the codes.
information on how every input file should be The Enrichment station allows configuring third
interpreted, and how it should be mapped to party or internal services that should be invoked to
internal formats and codes. Due to varying number enrich the data. For example, you may get specific
of data elements, formats and mapping rules, the peril data for every location from third parties and
best way to store this Metamodel is to leverage append to the data. It also runs the configured
‘No SQL’ databases. The Importer is a batch rules to flag specific risks for a deeper evaluation.
routine that imports ongoing feeds by leveraging Once the standardized and enriched data is
the Metamodel information. The Translator uses available, it will be sent to an underwriting
the translation engine to covert the input data workstation for further processing. The better
elements into standardized formats that can be quality, standardized data also enables the use of
used internally. The Code Mapper allows mapping analytical models, thereby providing quality
incoming codes to the industry standards such as insights to underwriters.
ACORD or internal standards. This functionality

L&T Infotech Proprietary 04 / 05

 Automating Data Intake Process in
Commercial Underwriting

Business Benefits
The solution provides following business benefits:

Reduction in the overall cycle time by as Improve decision making due to better quality,
much as 50% (calculated for large market enriched data that can be leveraged for
property risks) advanced analytics

Eliminate or reduce manual intervention needs

significantly, thereby reducing costs by as
much as 35%

About the Author

Amit Unde is an Associate Vice President and CTO for Insurance at L&T Infotech. He
leads L&T Infotech’s Insurance Solutions Office and Enterprise Architecture Practice
in North America. He has about 19 years of experience working with insurance
companies across the globe. He has a blend of technology and insurance domain
expertise, and has helped leading carriers, brokers and reinsurance firms in defining
their Enterprise Architecture and IT Strategy Roadmap.

Amit specializes in Commercial Underwriting and Risk Management Solutions, and

has been at forefront of leveraging modern technologies such as Location
Intelligence and Big Data Analytics, for better risk selection and pricing. He leads
development of L&T Infotech’s Underwriting and Risk intelligence solution called
AccuRUSITM.

LTI (NSE: LTI, BSE: 540005) is a global technology consulting and digital solutions Company helping more than 350 clients
succeed in a converging world. With operations in 30 countries, we go the extra mile for our clients and accelerate their
digital transformation with LTI’s Mosaic platform enabling their mobile, social, analytics, IoT and cloud journeys. Founded
in 1997 as a subsidiary of Larsen & Toubro Limited, our unique heritage gives us unrivaled real-world expertise to solve the
most complex challenges of enterprises across all industries. Each day, our team of more than 28,000 LTItes enable our
clients to improve the effectiveness of their business and technology operations, and deliver value to their customers,
employees and shareholders. Find more at www.Lntinfotech.com or follow us at @LTI_Global

[email protected]

L&T Infotech Proprietary 05 / 05