Transforming ESG Challenges into Opportunities: Enhancing Profitability in Commercial Insurance

In recent years, the insurance sector has been under growing scrutiny from institutions, regulatory bodies, and the public to quantitatively assess, monitor, and disclose the ESG (Environmental, Social, and Governance) performance of their commercial insured portfolios. However, acquiring ESG data and metrics for commercial clients, particularly SMEs (Small and Medium-sized Enterprises), remains a significant hurdle due to the lack of regulatory pressure and limited information available.

What practical solutions can address these challenges today? How can these obstacles be turned into opportunities? Learn how to access ESG data and boost the profitability of your commercial book of business by leveraging the proven correlation between ESG factors and loss ratios, all while supporting the insurance industry’s sustainability goals.

You will discover:

1. How to integrate a sustainability assessment into the commercial underwriting processes without involving the client in a tedious ESG questionnaire.

2. Which ESG data and key indicators are accessible, and how to determine their correlation with the insurance risk based on real case studies.

3. How to improve loss ratio by underwriting more sustainable and ESG-compliant businesses.

About the speaker, Mattia Bongini, Data Science Manager, CRIF:

With over a decade of experience in advanced analytics and machine learning, Mattia Bongini is a seasoned Data Science Manager at CRIF. He leads teams in developing cutting-edge analytics solutions for insurance and banking clients, focusing on sustainability, risk-based pricing, fraud detection, and marketing analytics.

Mattia has supported his clients with several impactful projects, including pricing sophistication models for consumer and commercial insurance, and the estimation of sustainability metrics for corporates, like GHG emissions, transition risk and biodiversity impact.

Prior to joining CRIF in 2018, Mattia contributed to statistical initiatives at the European Central Bank and held research positions at Université Paris-Dauphine and the Technical University of Munich, focusing on machine learning for complex systems and optimal control. He holds a Ph.D. in Applied Mathematics from the Technical University of Munich.