Simulation framework models 500 million household financial decisions
S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents
Multiagent SystemsArtificial Intelligence
Summary
Understanding how millions of households make financial choices helps predict economic trends. The authors created S2-MAS, a system that simulates the spending, borrowing, and repayment of 500 million pretend households based on real data. Their method uses a trained model to imitate how people decide about money, capturing differences by age, income, and other factors. This helps study how changes like credit limits affect overall consumption and debt over time.
What this means in practice
- •For economic policy analysts: Simulate large-scale financial behavior changes in households to evaluate economic policy impacts before implementation.
- •For financial product designers: Test how different credit products affect diverse household groups’ spending and repayment patterns using detailed synthetic agent simulations.
Authors
Yang Li, Di Wan, Yike Wang, Chujun He, Zongsi Xu, Xiyu Chen, Sheng Zhong, Deng Binjie, Zhenwei Guo, Hou Jun, Kunhan Guo, Weihao Lin, Tuo Zhou, Hai Liu, Ye Luo
Abstract
Simulating economic responses at society scale requires agents whose decisions reflect household circumstances and the effects of earlier actions. We introduce S$^2$-MAS, a society-scale multi-agent simulation framework built on 500 million synthetic household personas grounded in real-survey data. Its Genese engine separates decisions from state updates, while reusable financial scenarios and application ledgers track consumption, cash, debt and payments. FinL-mlx, a compact decision model trained with SFT + RLCD on 2.93 million examples, achieves 74.55% accuracy and 38.37% question-macro F1 in consumer financial-choice scenarios, outperforming Jev 1.13 and GLM-5.3-Flash on both measures. We evaluate eight financial task families and simulate 12 million distinct household agents in paired purchase-funding conditions. Jointly raising purchase goals and approved credit limits increases consumption, with responses differing across age and income groups. Education, employment and household-size differences persist after age--income standardization and mainly reflect transitions from deferral to purchase. Asset and debt groups differ in cash drawdown, repayment and closing debt. A 24-month panel varies purchase goals under a common credit product, with repayment and arrears updating subsequent offers. S$^2$-MAS links heterogeneous household decisions to evolving consumption, cash and repayment paths, supporting economic experiments across household groups, population scales and time horizons.