Projects / HackPrinceton Fall 2025
Award winnerBest Predictive Intelligence by Chestnut FortyConfidence: low
Forexery
A reinforcement-learning agent that trades USD/JPY using news sentiment plus technical signals.
Project facts
- Team
- 2 people
- Build
- software only
- AI
- ml model, llm api
Problem
Most retail forex traders lose money; technical indicators miss why markets move.
Solution
Trains an RL agent in a trading environment combining sentiment from news with technical features.
Demo moment
Team-described: compare the agent's returns against buy-and-hold.
Why it stood out
- organizer statedWon “Best Predictive Intelligence by Chestnut Forty” among 195 submissions.Source ↗
- team statedCombines why (news) and what (price) in one model.Source ↗
Lessons for your next hackathon
- Show training curves and a baseline when claiming trading results.
Similar situations
Projects that share domains, mechanisms or judging lenses — often with a different problem and stack.Tune the comparison.
Award winner · 2026
Detects market regimes from order-book microstructure and switches trading strategy before instability hits.
Shared: domains fintech · mechanisms visible engineering depth · lenses technical depth · ai ml model · stack python
Award winner · 2026
Upload a trade log to see scores for overtrading, loss aversion and revenge trading, with explanations and coaching.
Shared: domains fintech · mechanisms visible engineering depth · lenses technical depth · ai ml model, llm api · stack python
Award winner · 2025
AI agents that align schemas and merge data when two financial institutions combine.
Shared: domains fintech · mechanisms visible engineering depth · lenses technical depth · ai llm api · stack python
Award winner · 2026
A simulated market of AI trader agents to test your investment strategy before using real money.
Shared: domains fintech · mechanisms visible engineering depth · lenses technical depth · ai llm api · stack python
Award winner · 2025
A background browser extension that maps the concepts you study into a personal knowledge graph without asking you anything.
Shared: mechanisms visible engineering depth · lenses technical depth · ai ml model, llm api · stack python
Award winner · 2025
A computer-use agent that carries out multi-step desktop tasks from one instruction, built for a benchmark challenge.
Shared: mechanisms visible engineering depth · lenses technical depth
Sources
- https://devpost.com/software/forexery · devpost project · retrieved 2026-10-13
- https://hackprinceton-fall-2025.devpost.com/project-gallery · devpost gallery · retrieved 2026-10-13