Ortec Finance has unveiled a new case study in partnership with M&G Investments, demonstrating how its Scenario-Based Machine Learning (SBML) approach can redefine strategic asset allocation.
The technology introduces a new level of optimisation by enabling multiple objectives to be addressed simultaneously, with results assessed through a stochastic scenario approach to maintain both innovation and transparency.
The latest case study, which can be read here, builds on earlier research that showed SBML’s ability to overcome the limits of traditional optimisation methods, such as generating efficient frontiers while incorporating complex constraints. The collaboration with M&G Investments takes this a step further, applying 3D optimisation within Ortec’s GLASS platform. This allows insurers to pursue three goals in tandem: maximising assets above liabilities, maximising expected cumulative surplus in the worst 5% of scenarios, and minimising the Market Risk SCR Charge as a proportion of surplus assets. At the same time, the Market Risk SCR Charge itself remains constrained.
By incorporating these objectives together, insurers can explore a new frontier of efficient portfolios that more accurately balance competing needs.
One of SBML’s defining features is its transparency. Unlike opaque AI-driven models, SBML portfolios can be examined with existing GLASS tools, including contribution analysis. This allows users to understand why certain asset classes are weighted more heavily, fostering greater trust in the optimisation process and in the results produced.
The benefits demonstrated in the study highlight how SBML moves strategic asset allocation into a new dimension. With 3D optimisation, insurers can manage multiple objectives simultaneously while adhering to necessary constraints.
Ortec Finance plans to release SBML as a module within GLASS by the end of 2025.
Read the full case study here.
‘Read the daily FinTech news’
Copyright © 2025 FinTech Global
