Equity vs. BTC buy & hold
No snapshots yet — the bot writes one every 5 minutes once deployed.
Watchlist
live prices · change vs. 24h ago (crypto) or prior close| Symbol | Name | Price | 24h | Market |
|---|
Watchlist warms up after the next bot tick.
Open positions
| Symbol | Side | Size | Entry | Price | Lev | Stop | Target | Unrealized |
|---|
No open positions.
Trade history
| Time | Symbol | Action | Side | Price | Notional | P/L |
|---|
No trades yet.
Agent activity
No agent activity yet.
Mechanical twin — no-LLM control group
Three mechanical engines (trend / Donchian / mean-reversion, replicating the hackathon-bot design) over the shared risk core, on a separate $10k paper book. Same prices, same costs, zero LLM judgment — if the main desk can't beat this over time, the judgment layer isn't paying its way.
DCF value sleeve — 20-trading-day book
A separate $10k ledger holding the five cheapest names by discounted-cash-flow value-to-price, equal weight, long only, no leverage and no stops, rebalanced every 20 trading days. This is the desk's only signal validated point-in-time (21,927 observations, 20 symbols, 5 years, intrinsic value rebuilt from filings public at each date): cheapest-minus-richest quintile spread +0.378% at 20 days, ~0 at 5 days. It is deliberately outside the short-term trade path — the edge does not exist on the desk's horizon. Judge it against buy-and-hold, not zero: most of the absolute return is market drift, the spread is the edge.
| Symbol | Entry | Price | P/L % | Held since |
|---|
Sleeve is in cash — next rebalance will fill the basket.
DCF valuations — what the businesses are worth
Two-stage discounted cash flow on trailing free cash flow: growth fades to a 2.5% terminal rate, discounted at CAPM (live 10-year yield + beta × 5% equity risk premium), net debt subtracted. Foreign-currency filers are excluded — a TWD intrinsic value cannot be compared with a USD price. Only six names are re-valued per night on a rolling basis, so a row can be several days old — the price shown is the one captured when that valuation was computed, not spot, and upside is measured against it. It is a valuation, not a trade signal.
| Symbol | Price at valuation | Bear | Base | Bull | Upside | Disc. | Growth |
|---|
No valuations yet.
Signal quality vs. random entries
Forward returns after the desk's own entries, against random entries on the same symbol in the same direction over the same window. Edge is the difference. A negative edge means the timing is worse than a coin flip — the measurement exists to say so out loud. Horizons are counted in hourly bars, not clock hours: US equities trade ~7 hourly bars a session, so 24 bars is roughly 3–4 sessions for a stock and about a day for crypto.
| Cohort | Horizon | n | Signal | Random | Edge |
|---|
Where the drift lives — overnight vs. intraday
Equity returns split into close-to-open and open-to-close across the desk's tradeable US equities. The figures and the verdict below are generated from the current measurement, never stored — this desk once shipped a minimum-hold rule on a hardcoded claim that its own numbers had stopped supporting, so the sample size and t-statistic travel with every number here.
Nightly backtest — frozen rulebook (walk-forward)
The mechanical rulebook replayed over the trailing month each night after the NYSE close — the LLM layer is not simulated, so this is the rulebook's floor, not a forecast.
| Run | Rulebook | Trades | Win % | Return | Green days | Worst day | Max DD | BTC B&H |
|---|
First nightly run lands after the next NYSE close.