Willis Towers Watson introduces updated version of Emblem predictive modeling software

Bookmark and Share

Emblem 4.6 is capable of modeling and visualizing real-world customer behaviors quicker and with greater pricing accuracy

Arlington, VA (Oct. 25, 2017) – Willis Towers Watson, a leading global advisory, brokering and solutions company, has released an updated version of its Emblem predictive modeling software. Emblem 4.6 is distinguished by the addition of a technique to model complex customer behaviors involving multiple possible outcomes, in order to understand real-world dynamics more accurately and visualize risk more easily.

Emblem is an industry-leading software solution used in both commercial and personal lines to build predictive models that support a broad range of applications, including pricing premiums, more effectively. In addition to having a highly visual and intuitive interface, Emblem 4.6 now also performs 20% faster than the previous version on rich data sets, enabling significantly reduced decision cycle times.

The updated software, which allows insurers to fit models to vast data sets in seconds, builds on the last major release of Emblem in 2016 by introducing multinomial modeling, which has the ability to more accurately model behaviors with multiple outcomes. This enables users to detect previously unnoticed patterns in insurance claims and customer behavior experience within a single fast and robust modeling framework.

“This substantial improvement helps companies more accurately model the complex customer behaviors with multiple outcomes,” said David Ovenden, global director, Pricing Product Claims and Underwriting, Willis Towers Watson. “The ability to predict the purchasing behavior of customers presented with such propositions offers insurers a real commercial edge when operating in competitive markets.

“With competition intensifying, changes in regulation and distribution, and the ongoing redefinition of consumer expectations, we are seeing a clear and widespread focus on pricing sophistication and effective customer management. As part of that, interpretable and implementable analysis is becoming essential for product management. Emblem 4.6 supports all of this.”

What is multinomial modeling?

A multinomial model predicts the probabilities of a set of related events, and therefore also the probability none of those events occur. Multinomial modeling has the ability to model complex customer behaviors with multiple outcomes. In certain circumstances, it provides a more accurate representation of modeling outputs.

Examples of multinomial modeling uses include:

  • Multi-brand new business demand
  • Multi-product demand offering
  • Add-on package purchasing
  • Loan survival and delinquency
  • Claims tiering

About Insurance Consulting and Technology

Willis Towers Watson’s Insurance Consulting and Technology business has over 1,200 colleagues operating in 35 markets worldwide. It is a leading provider of advice, solutions and software — primarily to the insurance industry. Its consulting services help clients manage risk and capital, improve business performance and create competitive advantage — by focusing on financial and regulatory reporting, enterprise risk and capital management, M&A and corporate restructuring, products, pricing, business management and strategy.

About Willis Towers Watson

Willis Towers Watson (NASDAQ: WLTW) is a leading global advisory, broking and solutions company that helps clients around the world turn risk into a path for growth. With roots dating to 1828, Willis Towers Watson has 39,000 employees in more than 120 countries. We design and deliver solutions that manage risk, optimize benefits, cultivate talent, and expand the power of capital to protect and strengthen institutions and individuals. Our unique perspective allows us to see the critical intersections between talent, assets and ideas – the dynamic formula that drives business performance. Together, we unlock potential. Learn more at willistowerswatson.com.

Source: Willis Towers Watson

Tags: , ,