Paper Trader

Tempo — momentum at variable gearing · one review each market day, every decision logged.

Portfolio Value
$104,573.01
as of 2026-10-12
Total Return
+4.57%
+$4,573.01 since inception
Latest Day
—
session P&L
Sessions
26
since 2026-09-02
Cash
$-1,433.36
uninvested buffer
Overviewmandate, equity, what it holds
Mandate

A systematic momentum book that separates the two decisions most strategies fuse. Which names to own is cross-sectional momentum, the same blended 12-1 / 6-month / 3-month score the Fable account uses, top eight with a trend filter and hysteresis so winners are not churned at the rank edge. How MUCH of them to own is a separate, deterministic answer: the whole book is geared to a 22% volatility target, so exposure rises toward a 1.90x ceiling when the market is calm and falls to cash when it is not. The gearing uses the higher of a 20-day and a 60-day volatility estimate, which makes it deliberately asymmetric — the book de-levers as soon as the fast measure moves and cannot re-lever until the slow one agrees. Idle capital sits in cash rather than Treasuries, and the only diversifier is gold, both for the same measured reason: this contest credits no dividends, so a bond fund would hand back its entire return.

How it was decided

Eric's mandate of 2026-09-01 — 'I want AI to be the creator of the 5th strategy, your sole goal is to beat the other strategies over 1, 3, 5 and 10 year horizons.' Designed by Claude Opus 5 and chosen by measurement rather than argument: eight strategy families were built and raced against backtested reconstructions of the other books, through one engine on one dataset, over two windows so the answer could not be fitted to a single regime. The families that lost are published beside the one that won.

Equity Curve · from $100,000
Current Holdings · 9
SymbolMarket ValueUnrealized
GLD $16,216 -4.22%
CSCO $12,859 +7.01%
AMGN $11,929 +1.11%
MRK $11,474 -2.97%
AMD $11,444 +30.95%
TGT $11,302 -7.42%
CAT $10,479 +2.55%
LLY $10,334 +1.14%
INTC $9,970 +13.89%
Riskmeasured after the session, never shown to the agent
Attribution · market vs decisions · 2026-10-12

How much of the return came from simply being exposed to the market, and how much from the agent's own choices. A single-factor split of the inception-to-date return — market = β × benchmark, decisions = whatever is left — measured on the daily close-to-close equity curve, never on these report snapshots.

Total return
+4.73%
inception to date
Market
+0.33%
β × benchmark
Decisions
+4.40%
the residual
Cash drag
+0.02%
-1.4% in cash
The decision half is not yet distinguishable from luck. Alpha's t-statistic is 0.71, well short of the ~2 that would make it significant, so +4.40% of "decisions" is the honest arithmetic residual and not evidence of skill. Beta is well measured long before alpha is — that asymmetry is a property of the estimate, not a flaw in the book, and it takes a lot more than 26 sessions to resolve.
The regression behind the split
EstimateValueReading
Beta0.19 t = 0.59 · not yet distinguishable from zero
R²1.4% the benchmark explains little of this book's day-to-day
Alpha (annualised)+43.24% t = 0.71 · NOT significant
BenchmarkS&P 500 26 aligned sessions · 2026-08-26 → 2026-10-09
Today alone. The book moved −1.45% against a benchmark +0.59% — +0.11% of that was exposure and −1.56% was position selection. One day of a two-term decomposition is noise; it is here because the daily reading is what accumulates into the figures above.
FRTB Capital · standardised approach · 2026-10-12

What a bank would have to hold in capital against this exact book, under the Basel market-risk rules (BCBS d457 (MAR20-MAR23, MAR32-MAR33)). Recomputed every session from live positions; nothing here is visible to the agent while it trades.

Capital requirement
$38,694
SbM + DRC + RRAO
Of equity
37.0%
capital / portfolio value
Market-risk RWA
$483,672
capital × 12.5
Overstated. 1 name(s) (GLD) could not be classified from reference data and fell to the "other sector" bucket at a 70% risk weight — the regulation's own fail-closed rule. The number above is safe-direction wrong.
Components, buckets, and why DRC is the interesting line
ComponentChargeShare
SbM delta · high correlations bind $22,793 58.9%
SbM vega · no optionality in the book $0 0.0%
SbM curvature · linear payoff $0 0.0%
DRC — jump to default · LGD 100% $15,900 41.1%
RRAO · no exotic underlyings $0 0.0%
Total capital requirement$38,694100%
Equity buckets · MAR21.72
BucketRisk weightNamesNet valueKb
8 50% AMD, CSCO, INTC $34,272 $12,640
11 70% GLD $16,216 $11,351
5 30% AMGN, LLY, MRK, TGT $45,035 $9,407
6 35% CAT $10,479 $3,668
Why the second-biggest line is the interesting one. The DRC is jump-to-default: the issuer disappears overnight. Equity has no recovery, so Basel sets loss-given-default at 100% and charges an unrated name 15% of its market value — 41% of the requirement here, and nothing about hedging, forecasting or diversification reduces it. That the high correlation scenario binds is itself a readout: a long-only book is dearest when correlations rise, a hedged one when they fall.
Value at Risk · historical simulation · 2026-10-12

The loss this book exceeds on the worst few days in a hundred, measured by replaying 499 days of its own constituents' returns through today's positions. Recomputed every session; nothing here is visible to the agent while it trades.

VaR 99% · 1 day
$3,246
worst 1 day in 100
Of equity
3.10%
loss / portfolio value
ES 97.5%
$3,309
average of the tail beyond
VaR 99% · 10 day
$8,603
regulatory horizon
Quantiles, component VaR, the backtest, and what VaR will not tell you
ConfidenceHistoricalOf equity ParametricGapTail pts
95% $1,977 1.89% $2,269 −12.8% 25
99% $3,246 3.10% $3,208 +1.2% 5
ES 97.5% $3,3093.16% the average of the tail, not its edge
Why the 10-day figure is measured, not scaled. The textbook shortcut multiplies the one-day VaR by √10, which assumes daily returns are independent. Here that gives $10,265 against a measured $8,603 — 19.3% too high. Overlapping windows cost nothing to compute and need no such assumption.
Component VaR · at 99% · sums to the total
NameMarket valueWeightComponentShare
AMD $11,446 10.8% $750 23.4%
INTC $9,968 9.4% $710 22.1%
CAT $10,479 9.9% $365 11.4%
CSCO $12,859 12.1% $292 9.1%
TGT $11,302 10.7% $232 7.2%
LLY $10,330 9.7% $227 7.1%
AMGN $11,929 11.3% $224 7.0%
GLD $16,216 15.3% $216 6.7%
These are allocations, not a ranking. Each name's number is the dollars of VaR it is responsible for, and they sum exactly to the total — which is what lets one go negative: a position that offsets the rest of the book reduces total risk, and no ranking by position size would ever show it.
The part that makes it a measurement. Over 249 out-of-sample days the 99% threshold was breached 1 time(s) against 2.5 expected — Kupiec p = 0.281, verdict consistent with the model, Basel traffic light green. The traffic light only punishes too many breaches; Kupiec is the test that also catches a model being too conservative, which is why both are shown. Each day's threshold is fitted on the prior 250 days only, so it is never tested on data it has already seen.
Two different questions. Everything above shocks today's positions with market history. The account's own equity curve — 33 sessions, 17.2% annualised volatility — says what it has actually done: 95% VaR 1.50% · 99% VaR 1.85%. They diverge whenever the agent has been trading.
What VaR will not tell you. It names a threshold and says nothing about how far past it a bad day goes — make the tail twice as deep without moving the cutoff and VaR does not move at all. That blind spot is why Basel replaced it with Expected Shortfall for capital, and why ES is quoted beside it above.
Counterparty Risk · SA-CCR · 2026-10-12

Market risk is symmetric — the price moves, you win or you lose. Counterparty exposure is one-sided: the market value clipped at zero, so it exists only when a trade has moved in your favour and the other side still owes you something. A fully-paid share bought on an exchange has none of that. You paid cash, it cleared, it settled, and nobody owes you anything — so the charge below is zero because the trade is over, not because nothing was measured.

SA-CCR EAD
$0
α × (RC + PFE) · 0 derivative(s)
CVA capital
$0
spread risk, not default
Settlement in flight
$0
T+1
Custodial concentration
100%
one broker, everything
The derivation: SA-CCR terms, what was excluded, settlement, leverage and concentration
SA-CCR termValue
Derivative trades in the netting set 0
Replacement cost · max(V − C, 0) $0
Add-on aggregate · supervisory factors $0
PFE multiplier · floored at 5% 1.0000
PFE · multiplier × add-on $0
α · CRE52.1 1.4
Exposure at default$0
CVA capital · CRE55, BA-CVA reduced $0
Why · what never reaches SA-CCR
KindPositionsMarket valueReason
cash equity long 9 $105,991 fully-paid long share: bought for cash, centrally cleared and settled — no open obligation, so no counterparty exposure
Settlement is the one that is genuinely live. US equities settle T+1, so a fill from this session is a commitment against a leg that has not been delivered yet: $0 in flight, $0 past due, capital charge $0. Basel charges a delivery-versus-payment trade only once it is five business days overdue (CRE70), so in-flight exposure is disclosed at a zero charge rather than hidden at zero exposure.
Leverage · capability vs utilisation
ProvisionedMargin debitShort valueGrossNet
4× · shorting on · options L3 $1,433 $0 1.01× 1.01×
Leveraged. This is what makes the zeros above readable as a fact about today's positions rather than about the account's permissions: the book is provisioned for 4× margin, shorting and options, and is currently using 1.4% of the first and 0.0% of the second. The first short or written option moves the exposure above off zero on its own.
The counterparty that does exist. Alpaca (paper) holds $-1,433 of cash and $105,993 of securities — 100% of the book, by construction. Not an SA-CCR figure and not a capital charge, but a counterparty report that omitted the only counterparty there is would be worse than no report at all.
What this is really measuring. Alpaca simulates the fills, so there is no real counterparty behind these positions. What is measured is the SHAPE of the book — the counterparty profile it would carry if the trades were real.
Sessionsevery decision, in the agent's own words
Latest Review · 2026-10-12
Trades

No trades this session — held all positions.

Agent Reasoning
Today is not a rebalance day (next one due 2026-10-14, 21 days after 2026-09-23), so per the plan I'm holding the book as-is — no trades executed. Book summary: 9 names, ~104.3% gross exposure, fully invested with modest leverage. Day's movers: AMD leads at +30.9% and INTC +13.7% are the standout winners driving momentum; CSCO +7.0% and CAT/AMGN/LLY are mildly positive. Laggards are TGT -7.4%, GLD -4.2%, and MRK -3.0%. VIX at 15.4 keeps the regime in normal (non-defensive) territory, drawdown is a modest 2.7% off highs, well inside the 30% breaker. No closes, trims, or buys were made — this is a scheduled hold day, not an omission. Nothing to veto (no fraud/halt/delisting news flagged on any name) and no risk-desk actions since zero orders were submitted.
History · 8 most recent of 25 earlier sessions
2026-10-09 $104,829.27 — 0 trades

No trades this session — held all positions.

TEMPO — 2026-10-09: Not a rebalance day, book held as-is Today is day 16 of the 21-day cycle (last rebalance 2026-09-23), so per the strategy's own turnover discipline, no trades are executed — this is the plan working, not an omission. Book snapshot (9 names, fully deployed): GLD 15.5%, CSCO 12.2%, AMGN 11.2%, AMD 11.2%, TGT 11.0%, MRK 10.8%, CAT 9.8%, INTC 9.8%, LLY 9.7%. Leaders since entry are AMD (+34.7%) and INTC (+17.7%), driving the book's momentum tilt; laggards are TGT (-5.8%), MRK (-4.5%), and GLD (-3.8%), with AMGN/LLY/CAT roughly flat. Risk desk context: drawdown from HWM is a modest 2.4% (breaker armed at 30%, nowhere close), VIX 15.2 sits well under the 30/40 defensive/freeze thresholds, so no regime-driven size cuts apply — the quiet tape simply isn't a signal to act on outside the schedule. No closes, trims, or buys were placed; no vetoes needed (no fact-pattern breaks in any name); nothing was sent to the risk desk today. Next action is the scheduled rebalance.
2026-10-08 $105,389.67 — 0 trades

No trades this session — held all positions.

Today: 2026-10-08 — not a rebalance day. No trades executed. Book held as-is at $105,397 equity, gearing ~101.4% gross exposure (9 positions, cash -$1,433), consistent with the 21-day rebalance cadence last run 2026-09-23. Market is modestly soft (S&P -0.3%, NASDAQ -0.51%, VIX 15.4, still well below the 30 defensive threshold), and the book's day-over-day composition is unchanged: AMD remains the standout winner (+39.1%), INTC strong (+22.1%), while GLD (-5.3%), TGT (-6.8%) and MRK (-6.0%) are the drag. Drawdown from HWM is a benign 1.9%, circuit breaker armed but not triggered. No closes, trims, or buys issued — holding per plan.
2026-10-07 $106,218.42 — 0 trades

No trades this session — held all positions.

Today (2026-10-07) is not a rebalance day — TEMPO rebalances every 21 calendar days and the last rebalance was 2026-09-23. Per the strategy's rules, no trades are made; holding the book as-is is the correct action, not an oversight. Book summary: 9 positions, fully allocated across GLD, CSCO, AMD, AMGN, TGT, MRK, INTC, CAT, LLY. Standout movers: AMD +40.0% and INTC +25.0% are the big winners, while GLD -6.0% and TGT -6.4% are the laggards; the rest are roughly flat to modestly positive. VIX at 15.8 is well below the defensive (30) and freeze (40) thresholds, and drawdown from HWM is a modest 1.1% against a 30% breaker — regime is calm, no risk-gate constraints are binding. Action taken: None. No closes, trims, or buys — this is a hold day by design. No vetoes needed (no news-driven disqualifying events reviewed/required since no orders are being placed). Nothing was sent to the risk desk, so nothing to report as rejected.
2026-10-06 $106,463.31 — 0 trades

No trades this session — held all positions.

Not a rebalance day — no trades executed. TEMPO rebalances every 21 calendar days (last: 2026-09-23); this is scheduled hold, not an omission. Book snapshot: $106,462 equity, 9 names, fully invested with slight negative cash drag (-$1,433, i.e. ~101% gross exposure from gearing). Leaders: AMD +39.3%, INTC +28.5%, CAT +10.3%, CSCO +5.3%; laggards: TGT -6.3%, MRK -5.9%, GLD -4.6%, AMGN -1.8%, LLY flat (+0.3%). Market context: Broad tape firm today (S&P +0.52%, Nasdaq +0.57%, Dow +0.46%), VIX at 15.4 — well under the 30 defensive / 40 freeze thresholds, so sizing regime is normal. Drawdown from HWM is a benign 0.9%, nowhere near the 30% breaker. No veto triggers identified (no halts, fraud, restatements, or delisting news flagged on any held name) and no risk-desk rejections since no orders were placed. Holding as-is until the next scheduled rebalance.
2026-10-05 $105,303.61 — 0 trades

No trades this session — held all positions.

TEMPO — 2026-10-05: Not a rebalance day. No trades executed. Today falls between scheduled rebalances (last: 2026-09-23, next due ~21-day cycle), so per the plan the book is held as-is — this is deliberate low-turnover discipline, not an oversight. Book: $105,287 equity, 9 positions, roughly evenly weighted 9.6%–15.3% each. Leaders: AMD +37.9%, INTC +30.0%, CAT +4.9%, CSCO +3.3%. Laggards: TGT -6.8%, MRK -6.3%, GLD -5.1%, AMGN -2.6%, LLY -0.8%. Cash is -$1,433 (small margin use within the -92% floor). Market: S&P +0.11%, NASDAQ +0.57%, Dow -0.57%, VIX 15.9 (well under the 30 defensive / 40 freeze thresholds) — calm regime, no risk-gate constraints triggered. Drawdown from HWM is 2.0%, nowhere near the 30% breaker. No closes, trims, or buys issued; nothing to veto (no disqualifying news on any held name); no risk-desk rejections since no orders were placed. Standing by for the next scheduled rebalance.
2026-10-02 $107,099.12 — 0 trades

No trades this session — held all positions.

TEMPO — 2026-10-02: No rebalance, book held Not a rebalance day (last was 2026-09-23, next due at day 21). No trades executed — closes, trims, and buys are all skipped per the plan. Book: $107,102 equity, ~108.6% gross exposure (implied leverage from a -$1,433 cash balance), spread across 9 names. Winners: AMD +38.9%, INTC +37.4%, CAT +9.2%, CSCO +2.0%. Laggards: TGT -4.5%, MRK -4.5%, GLD -3.8%, LLY -1.6%, AMGN -1.2%. Market: SPX +1.08%, Nasdaq +1.48%, Dow +0.90% on the day; VIX 15.6 and falling (-4.6%), well under the 30 defensive / 40 freeze thresholds — regime is calm, no gearing adjustment triggered by vol today. Drawdown from HWM is 0.3%, nowhere near the 30% breaker. No veto candidates — nothing in the book shows fraud/halt/delisting/restatement news. No rejections, since nothing was submitted. Holding as-is.
2026-10-01 $105,560.70 — 0 trades

No trades this session — held all positions.

2026-10-01 — Not a rebalance day. No trades executed. TEMPO rebalances every 21 calendar days (last: 2026-09-23; next due ~10-14), so per the plan the book is held as-is — this is the strategy functioning, not a skipped review. Current gearing: ~$106.9k gross across 9 positions vs. $105.6k equity (cash -$1,433, modest leverage), with VIX at 16.6 — well below the 30 defensive / 40 freeze thresholds, so no regime-driven resizing applies. Broader tape is flat-to-up on the day (S&P +0.19%, Nasdaq +0.31%, Dow +0.01%) despite a soft week (-0.5% to -1.8%). Book leaders remain INTC (+32.6%) and AMD (+33.5%), the two momentum standouts carrying the book; laggards are TGT (-4.8%), GLD (-4.4%), and MRK (-3.7%). No position breaches the 25% cap, no circuit-breaker or drawdown issue (1.7% off HWM vs 30% breaker). No veto triggers identified — no fraud/halt/delisting news flagged on any held name. Action taken: none; holding through to next scheduled rebalance.
2026-09-30 $106,465.17 — 0 trades

No trades this session — held all positions.

No trades executed — not a rebalance day. Per TEMPO's 21-day cycle (last rebalance 2026-09-23), today's positions are held as-is; this is by design, not an oversight. Book snapshot: Equity $106,482, cash -$1,433 (~1.3% levered via margin), 9 names, roughly equal-weighted 10-15% each. Winners driving the book are AMD (+32.3%) and INTC (+30.3%), with CAT (+4.5%) and AMGN (+3.3%) also green; laggards are GLD (-4.0%), TGT (-2.6%), MRK (-1.7%), CSCO (-0.7%), while LLY is flat-to-up (+1.7%). Market context: S&P +0.29%, NASDAQ +0.5%, Dow flat, VIX 15.8 (down 1.4%) — calm regime, well below the 30/40 defensive/freeze thresholds, so no risk-desk throttling in play. Drawdown from HWM is a benign 0.8%. No veto conditions present (no fraud/halt/delisting news flagged on any name), no orders placed, nothing sent to or rejected by the risk desk.
Full session log · every session →