Ortec Finance has expanded its Scenario-Based Machine Learning (SBML) approach, and has showcased it through a case study with M&G Investments.
The case study shows how 3D optimisation can take strategic asset allocation into new territory. The method balances multiple objectives while retaining transparency through Ortec’s GLASS platform.
The study demonstrates how insurers can optimise for three goals simultaneously: maximising assets over liabilities, increasing expected cumulative surplus in the worst 5% of scenarios, and reducing the Market Risk SCR Charge as a percentage of surplus assets, while also constraining the charge itself.
Earlier research had shown SBML’s potential to overcome traditional optimisation limits, such as handling non-linear constraints and generating efficient frontiers. The collaboration with M&G adds a third dimension, giving insurers and asset managers new flexibility in portfolio design.
A distinguishing feature of SBML is its transparency. Unlike “black box” AI, the results can be fully analysed using GLASS tools, including contribution analysis, which explains why certain asset classes are weighted. This visibility helps insurers and asset managers gain confidence in both the optimisation process and outcomes.
According to the findings, SBML portfolios consistently adhered to constraints, outperformed traditional models, and delivered results more quickly.
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
