AI-Driven MPF Retirement Advisory System
Problem
Hong Kong’s Mandatory Provident Fund (MPF) system requires participants to actively select from a range of constituent funds within their employer-sponsored scheme, yet most participants lack the financial knowledge or time to make well-informed, dynamic fund-selection decisions. Retirement adequacy outcomes are systematically poor when fund allocation is not regularly reviewed.
Method
AQUMON developed an AI-driven MPF investment advisory system combining algorithmic goal-based personalisation, lifecycle and asset-liability management (ALM) informed optimisation, and explainable recommendation workflows. The system integrates personalised retirement-gap analytics, risk profiling, and constraint-aware fund selection within a compliance-ready architecture suitable for deployment in regulated insurance and pension distribution environments. Distributed computation enables real-time recommendation generation across large participant bases.
Deployment
The system has been deployed with multiple MPF trustees and insurance providers in Hong Kong, including AIA (integrated into the AIA+ mobile app) and BCT Group (MARIO, BCT’s market-first AI advisor). The platform is designed to support approximately seven million Hong Kong MPF participants, with cumulative assets under advice exceeding USD 10 billion.
Research connection
This project draws on doctoral and post-doctoral research in stochastic control and optimal withdrawal policy design. The production deployment extends those theoretical results into a regulated, real-world context.
