Rethinking Portfolio Optimization for Insurers
Traditional portfolio optimization techniques often fall short when dealing with multiple objectives, non-linear constraints, and the complexity of capital requirements that insurers face. To address these challenges, Ortec Finance partnered with Insurance Asset Risk to explore how Scenario-Based Machine Learning (SBML) can transform the optimization process.
In this on-demand webinar, Ashish Doshi of Ortec Finance and Iain Ritchie of M&G Investments discuss how SBML leverages stochastic scenarios and advanced machine learning to learn complex, non-linear portfolio dynamics — helping insurers better balance return objectives, risk appetites, and solvency constraints.
Speakers:
- Ashish Doshi, Senior Business Specialist, Ortec Finance
- Iain Ritchie, Insurance Solutions, M&G Investments
Key Insights from the Webinar
Moving beyond traditional models:
Conventional approaches like mean-variance analysis no longer capture the full range of objectives insurers care about. SBML enables forward-looking portfolio testing under thousands of scenarios, incorporating regulatory capital and liability considerations.
Phase One – Proof of Concept:
In collaboration with M&G Investments, the first case study aimed to maximize surplus mean and the 5% Conditional Value at Risk (CVar) while maintaining a constant market risk SCR charge.
“SBML produced an efficient frontier of viable portfolios, whereas traditional optimization often yielded only a single usable solution,” explained Doshi.
According to Ritchie, “One of the main advantages of SBML modelling is the efficiency it brings. It allowed us to identify viable portfolios quickly and focus on strategic client discussions.”
Phase Two – Expanding the Horizon:
The second phase added a third optimization objective — optimizing mean, 5% CVar, and market risk SCR simultaneously — creating an efficient plane of possibilities.
“The ability to optimize across returns, risk, and capital will be a significant enhancement,” Ritchie said. “It helps us assess trade-offs more holistically and identify portfolios that strike the right balance.”
Technology and Human Expertise in Balance
They both highlighted that SBML supports — rather than replaces — human decision-making. Transparency and explainability remain essential, with contribution analysis and stress testing helping to ensure results are both insightful and actionable.
Ultimately, SBML provides richer, data-driven insights to empower insurers, while keeping expert judgment at the heart of the process.
To learn more about Scenario-Based Machine Learning and how it can help optimize your insurance portfolios, please contact:
Contact
Hamish Bailey
Managing Director UK, Head of Insurance & InvestmentRelated Insights
-
14 November 2025Webinar: Optimizing Insurance Portfolios with Scenario-Based Machine LearningExplore how Scenario-Based Machine Learning helps insurers optimise portfolios by balancing returns, risk, and capital. Watch the webinar.
-
10 November 2025Webinar Strategic Integration of ICS into Investment Decision-MakingPart 1 of a four-part executive series for global insurers and insurance asset managers - Empowering Investment Strategy under the Insurance Capital Standard
-
10 November 2025Exploring the Strategic Implementation of the Insurance Capital Standard (ICS)
A four-part executive series for global insurers and insurance asset managers - Empowering Investment Strategy under the Insurance Capital Standard
-
06 November 2025Private assets in focus: Navigating investment decisionsWatch a series of webinars focused on addressing private asset challenges across the investment decision-making process.
-
06 November 2025Webinar recording: Harnessing scenario-based machine learning (SBML) for private asset investment decisionsDiscover how scenario-based machine learning can be leveraged to optimize diverse institutional portfolios aiming to increase their private asset allocations
-
05 November 2025Total Portfolio Approach for Institutional Investors: The Governance BlueprintLearn about the importance of governance in the Total Portfolio Approach (TPA) for institutional investors
-
29 October 2025Quarterly Outlook: Q2 2025The outlook is based on the Ortec Finance Economic Scenario Generator (ESG) and offers our perspective on recent developments in the economy and capital markets.
-
29 October 2025Supporting private assets investment decisions with risk and return scenario modellingLearn how Ortec Finance’s risk and return scenario modelling capabilities can support private asset investment decisions.
-
29 October 2025Supporting private assets investment decisions with GLASS’ private assets pacing and liquidity risk managementLearn how Ortec Finance’s GLASS’ pacing and liquidity risk capabilities can support private asset investment decisions.