56 lines
4.9 KiB
Markdown
56 lines
4.9 KiB
Markdown
# Chapter 00 — Why a Real Execution Trail Matters
|
||
|
||
Status: drafting. Claim inventory: see `README.md` ch. 00.
|
||
|
||
Most quant books are written backwards: the author knows the answer, then builds a narrative to fit it. Backtests are quoted as if they were the outcome, the fill price is assumed to be the signal price, and cost is a footnote. This book is written the other way: every claim that could survive contact with a trading desk must survive contact with a *trail* — a record of what was intended, what was decided, what was placed, and what actually filled, at what price.
|
||
|
||
This chapter sets the spine: the `tac-rd-book` execution trail, which records every live round end-to-end.
|
||
|
||
## The funnel is the minimal honesty structure
|
||
|
||
A live trading round on the TradeAC stack is a chain of five checkpoints:
|
||
|
||
```
|
||
targets (intent) → decided → placed (order) → filled → reconciled
|
||
```
|
||
|
||
The trail records each step as first-class evidence. A round is only settled when the funnel has been reconciled — targets versus decisions versus fills, with per-symbol residuals and roll-ups for cash/buying-power impact, slippage in basis points, and cost as a fraction of gross traded notional. `PROVEN` — this is the schema of `tac-rd-book` (`trail_query`, `book_reconcile`), the same tooling used for the live rounds this book cites.
|
||
|
||
Why this structure and not a spreadsheet of P&L? Because P&L is the *last* place problems show up. By the time net return is wrong, you no longer know whether the intent was wrong (bad signal), the decision was wrong (bad gating), the fill was wrong (bad execution), or the book was wrong (bad risk). A funnel isolates the four.
|
||
|
||
## What the trail proved that a backtest could not
|
||
|
||
The book's live ground truth is round 3 (target date 2026-08-17), the first fully reconciled round of the post-reset signal: `EVIDENCE#020 → round 3`.
|
||
|
||
- The funnel held under live conditions: **10 targets → 10 decided → 10 placed → 9 filled**. One order was cancelled, and one target (SLV) was skipped because its requested delta was zero.
|
||
- Realized slippage was **4.54 bps**; estimated cost **≈ $45** on $74,202.85 invested; turnover **0.74**.
|
||
- The intent included risk limits from the research campaign: a $5M liquidity floor that dropped 8 of the 50 names, a 12% size cap, 95% concentration cap, and a 10% drawdown pause. `EVIDENCE#020`.
|
||
|
||
None of these numbers — slippage in bps, cost as a fraction of gross, the ratio of filled to placed — exists in a backtest. A backtest assumes a cost model (on this stack, 5 bp open / 15 bp close / $5 minimum) and a fill at the close price. The trail records what the market actually charged. That is the difference between a research claim and a trading claim.
|
||
|
||
`TODO(evidence-needed: the round-3 reconcile's realized-cost-vs-model comparison once the position window closes)`
|
||
|
||
## Backtests are historical, not promises
|
||
|
||
Throughout this book, backtest metrics carry a warning label, not a hiding place: universe, date window, and whether the hypothesis was pre-registered before the run. This matters because TradeAC ran 31+ experiments; with that many draws, some positive results will be luck. The book is explicit about which runs were pre-registered (e.g. isolation runs exp 28–31) and which were exploratory. `REFERENCED` — multiple-testing/cherry-picking risk is standard research practice; see `references/` as it accrues.
|
||
|
||
The most important proof of this discipline is the clean-lake reset, which this book treats as a turning point rather than a footnote: the pre-reset reference signal did **not** reproduce on a rebuilt lake (`EVIDENCE#010 → exp 21`). Had the book quoted the pre-reset backtest as fact, it would have shipped a lie. The trail and the traceability loop are what allowed the desk to catch it. Chapter 06 tells that story in full.
|
||
|
||
## How to read this book
|
||
|
||
- Every claim is tagged `PROVEN` (traced experiment/round), `HYPOTHESIS` (unreproduced), or `REFERENCED` (external source). `EVIDENCE.md` maps each tag to the run, branch, and round behind it.
|
||
- Chapters 03–10 follow the research arc: what was tested, what was proved, what was refuted, and what moved performance. Refuted runs are cited as evidence too — knowing what *doesn't* work is how the desk avoided paying for it twice.
|
||
- Chapter 11 is the reality check: live execution against the research claims.
|
||
- Chapter 12 is the synthesis: the scoreboard of what actually improved performance and why.
|
||
|
||
## Open questions
|
||
|
||
- `TODO(evidence-needed: a second live round beyond round 3, to confirm slippage and funnel hold under a different market regime)`
|
||
- `TODO(evidence-needed: reconcile realized cost against the 5bp/15bp/$5 backtest model over a full position window)`
|
||
|
||
## Evidence cited in this chapter
|
||
|
||
| Tag | Source |
|
||
|-----|--------|
|
||
| `EVIDENCE#020` | round 3, `tac-rd-book`, trace 27 (branch `exp/27-scheduled-algo-retrain-on-2026-08-17-tac`) |
|
||
| `EVIDENCE#010` | exp 21, run `f1bd3c28…`, branch `exp/21-clean-lake-re-execution-of-the-tac-rd-ra` | |