jev-stock-decision-maker
Streamlit demo that feeds live market data and fundamentals into a 20-question Jev model scoring buy/hold/sell, valuation, health and risk.
Overview
JEV Stock Decision Maker is a Streamlit demo that turns live market data into structured investment decisions. It pulls prices, multi-horizon returns and valuation multiples for indices and sector and thematic ETFs via yfinance, plus fundamentals, margins, growth, debt and analyst targets for a chosen ticker, and builds a state document from them.
A 20-question Jev model then scores the overall action (BUY, HOLD or SELL), valuation attractiveness, balance-sheet strength, momentum and relative strength, macro sensitivity and risk, and upside probability and catalysts. A quick Q&A section allows follow-up questions grounded in the same state. The app is labelled demo only and not financial advice. Note that the README describes Noul as a short natural-language justification, which differs from TypeSafe's definition of Noul as a yes/no probability.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | What is the overall action for this stock? | BUY · HOLD · SELL |
| Score | How attractive is the valuation / how strong is the balance sheet (1-5)? | 1 · 2 · 3 · 4 · 5 |
How it works
- Fetch market and ticker data with yfinance
- Build a state document of fundamentals and market context
- Ask Jev a 20-question set of Choice and Score questions
- Display structured answers in the Streamlit UI
Strengths
- Structured, auditable outputs instead of free-form text
- Single state document reused for all questions
Caveats
- Demo only, not investment advice
- README's description of Noul does not match TypeSafe's yes/no definition
- No evaluation or backtest
Getting started
pip install -r requirements.txt, put JEV_API_KEY in .streamlit/secrets.toml, then `streamlit run app.py`.At a glance
- Type
- App
- Status
- prototype
- Language
- Python
- Runtime
- Streamlit
- Has code
- yes
- Has tests
- no
Use cases and integrations
How curated lists describe it
JEV Decision is a live demo that turns market data into structured decisions. It pulls real-time prices, valuation ratios and sector context, then runs a 20-question against TypeSafe Jev model to score buy/sell conviction, financial health and risk
logicrw/awesome-jev-projects
Frequently asked questions
What does Jev score?
Overall buy/hold/sell plus valuation, balance-sheet strength, momentum, macro risk and upside, across 20 questions.
Is it financial advice?
No, the author labels it demo only and not financial or investment advice.
Where does the data come from?
Live prices and fundamentals from yfinance.
Related projects
Local China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.
ProjectbetaPython, TypeScriptLocal stock decision service that sends market data and news to Jev or a local model and returns a policy-checked buy/sell/hold.
ProjectbetaTypeScriptPyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.
ProjectbetaPythonChinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.
ProjectbetaTypeScriptSelf-hosted trading analysis platform pairing Claude briefings with Jev probabilities for signals like thesis-breaking headlines.
Servicebeta- Jev-Trades★ 51
Next.js crypto dashboard where Jev judges each tick across timeframes and drives a SQLite paper-trading portfolio with automatic TP/SL.
ServiceprototypeTypeScript