# Arbiter Quant

- **Event:** [Built with Opus 4.7: a Claude Code hackathon](https://cerebralvalley.ai/e/built-with-4-7-hackathon)
- **When:** Apr 21 at 12:00 PM – Apr 27 at 2:00 AM (EDT)
- **Where:** Online
- **Team:** [Tam Nguyen](https://cerebralvalley.ai/u/FinAnoma)
- **GitHub:** https://github.com/Khaitam911/bep-Arbiter-Quant
- **Demo video:** https://youtu.be/1Xb5sdsM7_0
- **Gallery:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/14

Vietnam has 7 million retail trading accounts on a $200B market with almost no access to professional research tools. As someone close to this market, I built the tool I wished existed — a quant desk that speaks Vietnamese and reasons in Vietnamese market context.
The core idea: don't predict price — pick the right method for the current market. Arbiter classifies each trading day into a named market regime (e.g., bull_choppy, sideways_low_vol) using six features: trend, volatility, breadth, foreign flow, session phase, and news intensity. It then mines historical days that match today's regime and asks Claude Opus 4.7 to allocate 3-6 diversified paper trades across 11 strategies, citing bucket statistics, news sentiment, upcoming macro events, and the live portfolio in a single prompt.

---

Markdown version of https://cerebralvalley.ai/e/built-with-4-7-hackathon/hackathon/gallery/14. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt