# microsoft/MarS

MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model

Repository: https://github.com/microsoft/MarS
Canonical: https://ross.abutalabs.com/products/microsoft-mars
Language: Python
License: MIT
License Family: permissive
Last push: 2026-06-11T00:10:33+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 35, longevity 48
- inputs: {"age_days": 674, "days_push": 84, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1776, forks 189 (observed 2026-08-28T04:05:34.574539+00:00)

## What it is
MarS is a financial market simulation engine powered by a generative foundation model, developed by Microsoft. It provides tools for simulating order flow, analyzing stylized market facts, forecasting, and studying market impact.

## Use cases
- simulate financial market order flow with a generative model
- forecast future market dynamics via simulation
- analyze market impact of large orders
- generate stylized facts reports for simulated markets
- run interactive market simulation demos
- research market microstructure with deep learning

## When to choose
- you need to simulate or forecast financial market dynamics with ML models
- you are researching market microstructure or order agent behavior
- you want to study market impact of trades in a simulated environment

## When to avoid
- you need production trading or live market execution
- you require the pretrained model immediately, as it is still pending public release
- you work outside financial market simulation domains

## Facets
- artifact type: library
- maturity: active
- function: simulation, machine-learning, deep-learning, data-science, agent-framework
- domain: fintech, machine-learning, simulation, artificial-intelligence, data-science
- platform: python
- tags: financial-market-simulation, generative-model, market-microstructure, order-agent, forecasting, iclr-2025, linux

## Member repositories
- microsoft/MarS (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:34.574539+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:25:16.771037+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/MarS (fetched 2026-08-28T04:05:34.574539+00:00, sha ae478f6baf33)
- Data as of 2026-08-30T08:39:29.467469+00:00.