FinancialPredictionJev
Experiment testing how well Jev predicts financial markets; the author reports it does not do well, like most LLMs.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
FinancialPredictionJev is a small experiment using Jev to predict financial market movements. According to the list summary, the author found that, like most LLMs as of September 2026, it does not do well at this task.
It is a useful negative result: typed decision models are good at judging text against criteria, but that does not translate into forecasting markets. No README was available, so the method, data and metrics are unknown.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Will this asset go up or down?(inferred) | up · down |
How it works
- Present market information as state
- Ask Jev for a directional prediction
- Compare predictions with outcomes
Strengths
- Reports a negative result
- Helps set realistic expectations for decision models
Caveats
- List-only; method and data unknown
- Not a trading tool
At a glance
- Type
- Project
- Status
- research
Use cases and integrations
How curated lists describe it
Using Jev to test how well it predicts financial markets(just like most llms as of september 2026, it doesnt do that good).
hellogumbo/awesome-jev
Frequently asked questions
Can Jev predict markets?
The author reports it does not do well.
Is code available?
The repository exists, but no README was reviewed.
Should I trade with it?
No, it is an experiment with a negative result.
Related projects
Pre-specified study running Jev and GPT-4.1 as 300 synthetic survey respondents; question format mattered more than model.
ProjectresearchPythonHypothesis-driven experiments characterising the Jev API, intended to inform a future football prediction product.
ServiceresearchPythonLocal China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.
ProjectbetaPython, TypeScriptPyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.
ProjectbetaPythonTrade Arena proof of concept comparing trading strategies on 13 US stock funds, grown out of a pre-registered Jev study.
ProjectprototypePythonStock terminal that gathers live evidence via Valyu and asks Jev for the probability a stock trades higher in 30 days.
ProjectprototypeTypeScript