← Portfolio home

Morning Note · Paper Portfolio · mangostracker.ai

Overnight session

Tuesday, November 17, 2026 — read before the market opens.

AMZNSELL $257.75
NEMSELL $110.31
AVGOSELL $333.40
WMTBUY $128.41
Portfolio value
$46,403.12
Since inception
-7.2%
-$3,596.88
Cash reserve
$72.57
0% of book
Deployed
100%
23 open positions

Tonight's activity

4 trades placed in the latest session.

SELL AMZN
Shares
0.6276
Price
$257.75
Total
$161.76
Cash after
$278.46

Trimmed ~20% of AMZN as RSI broke below the 50 momentum floor (55.4->45.4 over 5 sessions), tracking the confirmed Nasdaq AI-capex/regulation selloff since 11/5 (midterm data-center-regulation fears) that directly threatens AWS capex spend; keeping the core position.

SELL NEM
Shares
2.7666
Price
$110.31
Total
$305.18
Cash after
$583.64

Trimmed ~20% of NEM as RSI broke down a 5th straight session (52.84->42.21) on continued gold-price weakness; consistent with the repeated pattern of de-risking this name on confirmed downtrends, keeping a residual stake.

SELL AVGO
Shares
0.4167
Price
$333.40
Total
$138.93
Cash after
$722.57

Trimmed ~15% of AVGO as RSI went choppy and closed below the 50 floor (58.99->48.97) amid the broad AI-datacenter-regulation selloff that directly targets the networking-chip growth thesis this position is built on; keeping the core.

BUY WMT
Shares
5.0619
Price
$128.41
Total
$650.00
Cash after
$72.57

Adding to WMT: clears the GQM bar clean (ROE 22.3%, fwd EPS growth 11.8%), RSI(14) climbed steadily 5 straight sessions (64.5->69.0) as the staples/defensive rotation accelerates on confirmed strong Oct sales (total comps +11.1% YoY); sizing up the clearest sustained-momentum winner in the book while AI/semis sell off.

Updated prices for 190/193 names (ABB, CFLT, RMB failed fetch again, skipped as usual). Confirmed via news a real, catalyst-driven AI/semi selloff since 11/5 (midterm AI-datacenter-regulation fears, Nasdaq into correction, chips hit hardest) with rotation into staples/utilities/defensives - RSI across NVDA/GOOGL/MU/META sat in the 20s-40s while COST/BRK-B/DUK/PG/KO/PEP/SO showed clean sustained uptrends. Checked GQM fundamentals on the top rotation candidates (COST growth 9.8%, CEG growth 7.4%, DUK/AEP/SO ROE under 15%, PEP/PG growth too low) - none cleared the 10%/15% floor for a new buy, so no new names opened. Among holdings, trimmed three names showing confirmed RSI breakdowns tied to the selloff: AMZN 20% (RSI 55->45, AWS capex-regulation exposure), AVGO 15% (RSI 59->49, networking-chip AI-datacenter thesis directly in the regulatory crosshairs), NEM 20% (RSI 53->42, continued gold weakness). Redeployed into WMT (+$650, 5.0619 sh) - the cleanest sustained-momentum winner in the book (RSI 64.5->69.0 five straight sessions, GQM clean at ROE 22.3%/fwd growth 11.8%) riding the confirmed defensive rotation and strong Oct comps (+11.1% YoY). Left HON, ALSN, UPS, GE, TXN, ANET alone despite mild RSI cooling since none broke the 50 floor and no fresh negative catalyst confirmed - avoiding trimming on first cooldown per mandate. Ending cash $72.57.

How it picks

The mechanics behind every session.

Every weekday morning, before the market opens, the bot reads the trailing month of daily closes for a maintained watchlist — hand-picked, not an index feed, but deliberately balanced rather than tilted: roughly equal representation across technology, communication services, consumer discretionary & staples, healthcare, financials, energy, industrials, materials, utilities, and real estate, plus a few broad (not sector) index ETFs. No sector gets a head start — it looks for the best confirmed trend wherever it shows up, not noise, and checks anything that looks news-driven against an actual search before treating it as a reason to trade.

These rules are enforced by the server that executes each trade, independent of what the model decides — a trade that breaks one is simply rejected, not just discouraged.

Ready before the bell?

Yes — with one timing nuance worth knowing if you're mirroring this yourself.

~05:00 AM ET
The job fires (9:00 AM UTC, weekdays). It reads yesterday's closing prices for the full watchlist — the freshest data that exists at this hour, since the market hasn't traded yet today.
~05:05–05:15 AM ET
Trades are decided, booked into the simulation at that closing price, and this page updates.
9:30 AM ET
The real market opens — roughly four and a half hours after the decisions were made.

The nuance: these fills are booked at yesterday's close, not this morning's open. Mirroring a trade yourself at 9:30 fills at whatever that morning's actual opening print is — usually close, but it can gap on overnight news.

Notes

This is a paper-trading simulation running against real market data, not a real brokerage account. No commissions, spreads, or slippage are modeled. Treat this as a transparent log of the reasoning, not a signal to act on. Not investment advice.