Guide
How it works
A practical map of the simulator: how prices are built, what each screen is for, and how paper trading fits in. This is education about the app — not financial advice, and not real securities.
At a glance
You're paper-trading model-implied "shares" of players. Prices blend anchors, history, and new games; the UI is built so you can sanity-check moves against charts and season context — not chase one noisy stat.
The price engine
How a model price comes together
Anchor & history
Each listing starts from an opening anchor and prior-season productivity. That keeps prices from whipsawing on tiny samples early in the year.
Live games
As games land in your dataset, performance feeds the model. The price is a smoothed signal — it carries season context, not just the last box score.
What you trade
The number you see is the model’s latest quote for that player. It updates with your pipeline’s data, not with real-world order books or news.
Navigation
Where to click in the app
Market
Go →- Search by name or team; sort by price or recent change.
- Each row shows price (2 decimals), team, last game date, and move vs the prior game in your file.
- Click a row or Open to go to that player’s detail page.
Player page
Go →- Ticker, team, last game date, and season label sit up top for orientation.
- Charts compare model price to game score over time — zoom the ranges to see stretches, not just endpoints.
- The trade panel buys and sells whole shares at the latest model price.
Portfolio
Go →- Paper cash, position value, and total equity — same framing as a simple brokerage view.
- Use it to test sizing and holds against the same quotes the model publishes.
Charts & game score
On a player page, game score is that night's Hollinger-style summary from the box score. Model price can stay elevated after a soft night because the path carries prior games and season structure — use the chart window and season averages to see whether a move is a blip or part of a trend.
Practical tips
- Compare the latest point to the season line — not only to yesterday.
- Resize or pan chart ranges when you want a streak vs full-season context.
- Remember: both series come from your dataset file — missing rows behave like missing games.
Execution
Paper trading, simply
You start with paper cash. Orders are whole shares at the latest model price shown on that player — there's no bid/ask spread or slippage simulation. Your portfolio rolls up cash, mark-to-model position value, and total equity so you can rehearse allocation ideas on the same timeline as your ingested games.
Lot size
Whole shares only
Fill price
Latest model quote on submit
Balance
Cash + positions = equity
Caution next to a price
A warning means this player has no minutes logged in 2025-26 in your dataset file — injury, inactive, or data lag. The price may still reflect older seasons or the model anchor; treat it as stale relative to current floor time until your file catches up.
Glossary
Terms you'll see repeated
- Model price
- The simulator’s valuation for one share of a player at the latest ingested game — not a market quote from any exchange.
- Game score
- Hollinger-style single-game summary from the box score. A quiet night doesn’t have to tank price if the model still weights season strength.
- Paper cash / equity
- Virtual balance and portfolio totals only. No deposits, withdrawals, or real P&L.
- Change vs prior game
- Difference in model price from the previous game row in your dataset for that player — useful for scanning the board.
Simulation only — paper currency and model-driven prices. Nothing here is investment advice, a prediction of real athletic or financial outcomes, or an offer of securities. If your pipeline or dataset changes, replay history and labels change with it.