Professor Dr. Tan · CP3405 TR2 2026

★ Exemplary Sprint Submission
What excellent work looks like

This is a model answer for Week 2 (sprint window: 26–30 May 2026). Study every section. Your submission does not need to reach the same conclusions — but it must show the same structure, discipline, and honest reasoning.

Team: Exemplary Group A Week: 2026-W22 Filed: Sat 24 May 2026 21:47 SGT GitHub: evidence/ folder complete
📆

Daily vs Weekly Data — Our Recommendation

We track weekly numbers, not daily. Our prediction is a weekly call — what SPX, NDX, and IWM will do by Friday's close versus last Friday's close. The only number that tests that prediction is the Friday-to-Friday change. Daily data is noise relative to the question we are asking, and recording it every day would add 5× the work without improving our analysis.

Weekend: Pull last week's data

Finviz 1W view + Yahoo Sectors 5D view immediately after Friday US close. Screenshot both. Record SPX, NDX, IWM, sectors. This is your baseline for the week's prediction.

Wednesday: One-line mid-week check

Not a full data pull. Just one line in the learning log: "As of Wednesday, SPX is at X — [ahead of / behind / in line with] our prediction. Key event that shifted the picture: Y." Keeps the team engaged without daily burden.

Following weekend: Record actuals

After Friday US close, pull Finviz 1W and Yahoo Sectors 5D again. Record actual % changes for SPX, NDX, IWM, and all 11 sectors. Compare to prediction. Score calibration. Prepare Monday presentation.

📊

Step 1 — Last Week's Actuals (19–23 May 2026)

Data Pull

Source: Finviz futures_performance.ashx (1W view) + Yahoo Finance sectors (5D view). Screenshots taken Saturday after US Friday close and committed to evidence/finviz_1W_2026-W21_Sat.png.

Primary Indices — SPX / NDX / IWM

SPX
+1.0%
Close: 7,473
8th straight weekly gain
NDX
+0.7%
Close: ~21,100
Lagged SPX — tech breadth flat
IWM
+2.7%
Close: 2,869
Best performer — oil drop lifted small caps
VIX
16.70
+1.2% on week
Calm — market cautious not fearful
10YR
4.60%
1-year high
Hit Monday, eased by Friday
OIL
−5.7%
~$61–62 WTI
Iran deal talk drove the drop
GOLD
−0.4%
$4,523
Near all-time high, slight pullback
BTC
−2.5%
~$75,400
Risk appetite muted

Sector ETF Scorecard — Week 21

ETFSectorWeekly %Signal
XLEEnergy+5.7%Led all sectors. Iran deal talk — energy stocks bid on geopolitical premium despite oil price falling.
XLVHealthcare+0.9%Defensive outperform. Steady through the macro noise.
XLPConsumer Staples+0.7%Defensive bid early week. Rotation into safety.
XLKTechnology+0.1%Barely positive. Nvidia beat helped but rate pressure at 4.60% yield capped gains.
XLCCommunications−0.4%Marginal lag. Ad spend concerns mild.
XLFFinancials−0.3%Banks dragged despite rising yields — credit concern offset rate benefit.
XLIIndustrials−1.1%Growth/cyclical pressure under elevated yields.
XLYConsumer Disc.−2.4%Consumer spending fears. Rate-sensitive. Worst large-cap sector ex-real estate.
XLUUtilities−2.7%Bond proxy crushed by 4.60% yield hit. Most rate-sensitive sector apart from XLRE.
XLREReal Estate−2.6%REITs = rate-sensitive. Yield at 1-year high is direct headwind.
XLBMaterials−3.0%Worst sector. Global growth demand worry + strong dollar pressure.

Week 21 story in one sentence: The 10-year yield hitting a 1-year high of 4.60% Monday was the defining event — it crushed rate-sensitive sectors (XLRE, XLU, XLY) while energy stocks oddly led despite oil falling, driven by geopolitical Iran deal positioning and volume flows.

🔬

Step 2 — Three Agent Outputs (Built Before Any AI)

Always do this first

Critical rule: These three outputs are written by the Almanac Lead (R3), Macro Lead (R4), and Technical Lead (R5) before anyone opens an AI tool. The point is to form your own evidence base independently. The AI synthesis then challenges it — not replaces it.

📅 Almanac Agent Output — R3 · Filed Saturday 21:12 SGT MONTH: May 2026
CYCLE CONTEXT: 2026 = Midterm election year. Q2–Q3 is the "Weak Spot" of the 4-Year Cycle. Almanac 2026 Outlook explicitly flags tougher trading through Q3 before a Q4 "Sweet Spot" rally. Historical Dow Q2+Q3 midterm avg: −2.0%. S&P: −2.5%. Nasdaq: −6.6%.

MAY VITAL STATS:
 · S&P: ranks #8 of 12 months. Up 61% of years. Avg +0.3% normally. Midterm year May avg: −0.7%.
 · Nasdaq: ranks #5. Avg +1.1%. Still a seasonal positive for tech specifically.
 · IWM: ranks #4. Avg +1.3%. Best historical May index — but midterm year avg −1.0%.

MEMORIAL DAY WEEK PATTERNS (26–30 May):
 · Memorial Day week: Dow down 17 of last 29. Moderate bearish pattern.
 · Day after Memorial Day (Tue 27 May): Dow down 8 of last 10. Recent trend clearly bearish.
 · Week after options expiration: S&P up 30 of 45, avg +0.40%. Moderate bullish pattern. CONTRADICTS above.
 · Friday before Memorial Day (Fri 23 May, now past): Dow mixed, avg −0.05%. Confirmed low volume.

SECTOR SEASONALITY (active signals from p.94):
 · Banking (XLF): seasonal SHORT window active May–July. Avg −6.3% historically.
 · Gold/Silver: seasonal SHORT begins mid-May. Avg −6.8%. Note: contradicts current elevated gold price.
 · Materials (XLB): seasonal SHORT May–October. Avg −5.1%.
 · Technology (XLK): still in seasonal LONG window through July. Avg +10.9%. Key positive.

ALMANAC SEASONAL BIAS: Cautiously bearish-neutral.
CONFIDENCE: LOW–MEDIUM. Two opposing week-level patterns. Midterm cycle headwind dominates.
THESIS: "Seasonality suggests caution in a midterm year late-May window, particularly for Dow/IWM. Technology seasonal long provides the one clear bullish offset. The Memorial Day week bearish tendency reinforces macro pressure from elevated yields."
Source: Stock Trader's Almanac 2026, pp. 65–66, 94. Accessed Sat 24 May 2026.
📰 Macro / News Agent Output — R4 · Filed Saturday 21:28 SGT FED / RATES:
 · Current Fed rate: 3.50–3.75% (held at April 29 FOMC meeting)
 · Next FOMC: June 17, 2026. CME FedWatch: ~96% probability of hold. No cut expected until September at earliest.
 · Tone: hawkish hold. Kevin Warsh sworn in as new Fed Chair on May 22 — known hawk. Market watching for tone shift.
 · 10-Year yield: 4.60% — hit 1-year high Monday. Eased to ~4.55% by Friday as oil fell.

OIL / IRAN — KEY DRIVER THIS WEEK:
 · WTI crude ~$61–62, down ~6% on the week. Trump comments + Iran deal draft rumours drove the drop.
 · CRITICAL: Iran deal is NOT confirmed. Both sides remain apart on Strait of Hormuz toll issues.
 · Binary risk: deal confirmed → oil stays low, yields ease, stocks rally. Talks collapse → oil spikes $6+, yields rise, stocks sell off.

COMING WEEK CALENDAR (W22: 26–30 May 2026):
 · Monday 26 May: US MARKETS CLOSED (Memorial Day). 4-day trading week.
 · Tuesday 27 May: Consumer Confidence. AutoZone, Zscaler earnings.
 · Wednesday 27 May: New Home Sales. Marvell (MRVL), Salesforce (CRM), Snowflake (SNOW) earnings.
 · Thursday 28 May: GDP 2nd estimate + PCE inflation — MOST IMPORTANT DATA POINT OF THE WEEK.
   PCE ≥ 2.8% YoY → yields spike, stocks sell off. PCE ≤ 2.5% → yields ease, stocks rally.
 · Friday 29 May: No major data.

CONTEXT — NEW FED CHAIR: Kevin Warsh is a known hawk who has criticised the Fed for moving too slowly on inflation. His tone at first public appearances will be watched closely. Any hawkish signal from him could add to yield pressure.

MACRO BIAS: Cautious / binary-risk dominant. PCE Thursday is the week's swing event.
CONFIDENCE: LOW. One data point (PCE) could reverse the entire week's direction.
📈 Technical Agent Output — R5 · Filed Saturday 21:44 SGT · Charts: evidence/charts_2026-W22/ SPX (S&P 500) — DAILY CHART:
 · Last close: 7,473. Price is ABOVE 8 EMA (~7,420) and ABOVE 21 EMA (~7,380).
 · 8 EMA above 21 EMA: YES. EMA condition: ZONE 1 (Bullish) — both rising, price above both.
 · Trendline: Uptrend line from March lows connecting ~7,050 → ~7,200 → ~7,350. Price above trendline. No break.
 · Resistance 1: 7,500 (round number, not yet broken). Resistance 2: 7,517 (May 14 high — all-time high).
 · Support 1: 7,350 (confluence of 21 EMA + trendline — KEY LEVEL). Support 2: 7,200 (prior breakout).
 · Breadth warning: only 57% of S&P 500 stocks above their 200-day MA. Narrow rally.

NDX (Nasdaq 100) — DAILY CHART:
 · Price above both EMAs. Zone 1 intact. Slightly underperformed SPX last week (+0.7% vs +1.0%).
 · Key resistance: 21,500 round number. Key support: 20,800 (21 EMA area).
 · Breadth: only 43% of Nasdaq stocks above 200-day MA — notably weaker than S&P breadth. This is the biggest technical warning.

IWM (Russell 2000) — DAILY CHART:
 · Outperformed massively last week (+2.7%). Price above both EMAs. Zone 1.
 · Resistance: 2,900 (round number — not yet broken). Support: 2,800 (21 EMA).
 · Note: IWM outperformance driven by oil drop and Iran deal hope, not fundamental change. Needs follow-through above 2,900 to confirm.

TECHNICAL BIAS: Neutral-Bullish. EMA structure intact across all three indices.
KEY WARNING: Narrow breadth (57% S&P, 43% Nasdaq) is the primary structural concern. A handful of mega-cap stocks are carrying the indices.
INVALIDATION: SPX close below 7,350 = trendline + 21 EMA break. That shifts bias to Bearish.
Charts annotated and committed: evidence/charts_2026-W22/spx_daily.png, ndx_daily.png, iwm_daily.png
🤖

Step 3 — Multi-LLM Comparison Table

R6 · LLM Synthesis Operator

All four models received the identical prompt with the three agent outputs above pasted in. Responses recorded Saturday 24 May 2026, 22:05–22:18 SGT. Raw files committed to evidence/llm_responses_2026-W22/.

Claude (Anthropic)

Neutral-Bullish
SPX: +0.3% to +0.9% · Medium

Led with oil drop reducing inflation pressure as primary bull. Flagged PCE Thursday clearly as binary risk. Did not mention low-volume holiday week amplification. Reasoned carefully, moderate tone.

ChatGPT (OpenAI)

Neutral
SPX: −0.5% to +0.8% · Low–Med

Widest uncertainty band of the four. Emphasised 4-day shortened week as a source of unpredictability. Flagged 10-year yield gravity most strongly. Most cautious overall. Breadth concern noted.

Gemini (Google)

Neutral-Bullish
SPX: +0.2% to +1.0% · Medium

Most bullish of the four. Leaned heavily on oil narrative and IWM outperformance as broadening signal. Acknowledged PCE risk briefly. Did not weight the new Fed Chair Warsh hawkish factor.

DeepSeek

Uncertain
SPX: −1.0% to +1.0% · Low

Most conservative. Flagged narrow breadth (43% NDX) as a structural fragility most explicitly. Also noted that Berkshire's $397B cash hoard and smart money cashing out is a late-cycle signal. Only model to raise this point.

DimensionClaudeChatGPTGeminiDeepSeek
Weekly RegimeNeutral-BullishNeutralNeutral-BullishUncertain
SPX % estimate+0.3% to +0.9%−0.5% to +0.8%+0.2% to +1.0%−1.0% to +1.0%
NDX % estimate+0.2% to +0.7%−0.5% to +0.8%+0.3% to +1.0%−1.5% to +0.8%
IWM % estimate−0.5% to +0.8%−1.0% to +0.6%−0.3% to +1.0%−2.0% to +0.5%
Top supporting reasonOil drop → inflation relief → yield easeShortened week, thin volume, upward drift biasOil + IWM broadening = health signalNo model: breadth too narrow for confidence
Top contradictionPCE Thursday binary risk10-year yield gravity at 4.60%Iran deal unconfirmed = oil spike riskSmart money cashing out (Berkshire $397B cash)
Missed by all 4?None explicitly flagged: thin-volume PCE amplification effect + new Fed Chair Warsh's first hawkish signals expected this week

Consensus reading: 3 of 4 models lean cautiously bullish-neutral. DeepSeek is the outlier with "Uncertain" — its breadth and smart money concerns are valid. The % range spread is wide (from −1.0% to +1.0% when you look across all models) — this is a signal that no model has high conviction. That tells you something: if four well-trained AI models cannot agree, the week is genuinely uncertain. State that honestly.

🧠

Step 4 — Human Score

R7 · THE DIFFERENTIATOR

This is where your team earns its marks. If this section sounds like a summary of what the AI models said, you have not done the Human Score correctly. What did YOUR TEAM see that none of the four AIs adequately weighted?

Dimension AI Said Team Team's Reasoning
Macro/News Weight
How strongly does macro drive direction this week?
+1 −1 The AI consensus treated the oil drop as a clean bullish signal. We disagree. The Iran deal is unconfirmed — a collapse means oil spikes $6+ in one session. That binary risk makes the macro environment more fragile than +1 implies. New Fed Chair Warsh's hawkish reputation adds further uncertainty.
Technical Structure
What does the chart say?
+1 +1 Agreed. EMAs in Zone 1, trendline intact, price above 7,350 support. However, we attach a stronger caveat to the NDX breadth warning (43%) than any of the four AIs did. We scored +1 but flagged it as a low-conviction +1.
Almanac Seasonal Weight
How much should seasonality influence the call?
0 −1 Claude and Gemini both scored seasonal as neutral/mixed. But we specifically looked at the midterm year row: −0.7% S&P average in May of a midterm year. The AI models did not give the midterm cycle context enough weight. We score −1.
AI Agreement Quality
How much do we trust the consensus?
+1 0 3 of 4 models lean bullish but the % range spread spans 2 full percentage points (−1% to +1%). When the models agree on direction but disagree sharply on magnitude, that is not genuine conviction — it is AI averaging toward a safe middle. We reduce to 0.
Wild Card — Human Observation
What did none of the AIs raise?
0 −1 This is our key human insight: The PCE data releases Thursday 28 May into a 4-day holiday week with significantly lower-than-normal trading volume. Low-volume environments amplify price moves in both directions. A hot PCE print on Thursday with thin liquidity could cause an outsized selloff — 2× or 3× what the same print would cause in a normal full week. None of the four AI models mentioned this volume-amplification dynamic. We scored it −1.
Human Score Total
−2
(−1 Macro + 1 Technical + −1 Almanac + 0 AI + −1 Wild Card)
Team verdict: Neutral-to-Cautious

We are slightly more cautious than the AI consensus of Neutral-Bullish. Our Human Score of −2 pushes us to the cautious side without calling outright bearish. The PCE wild card is the decisive factor — if it comes in hot into a thin-volume Thursday, the week could reverse sharply.

📌

Step 5 — Final Predictions (Week of 26–30 May 2026)

Locked Saturday 21:47 SGT

This prediction was committed to GitHub at 21:47 SGT Saturday 24 May 2026. File: prediction_2026-W22_GroupA.md. The commit timestamp is the immutable record. It cannot be changed. The team owns this call.

Team Alpha · 2026-W22 · Filed Sat 24 May 21:47 SGT
Primary Indices
SPX UP −0.2% to +0.6% MEDIUM Narrow range — PCE binary risk constrains conviction
NDX UP −0.2% to +0.7% LOW Tech seasonal long offsets breadth concern
IWM FLAT −1.0% to +0.5% LOW Last week's outperformance driven by Iran hope, not fundamentals
Sector Calls
Top sector (most likely to lead): XLK — Technology Seasonal long window active. Marvell + Salesforce earnings catalyst.
Bottom sector (most likely to lag): XLRE — Real Estate 10-year yield at 4.60% is direct headwind. No relief catalyst.

All 11 Sector ETF Direction Calls

XLKTechnologyUpSeasonal long + tech earnings week
XLCCommunicationsUpTech correlation + ad sentiment stabilising
XLVHealthcareFlatDefensive bid fades if risk-on continues
XLPCons. StaplesFlatDefensive hold — no strong catalyst either way
XLEEnergyFlatIran binary — cannot call direction with confidence
XLFFinancialsDownSeasonal short active. Credit risk + Warsh hawkish
XLIIndustrialsDownGrowth slowdown concern. Yield pressure continues
XLYCons. Disc.DownConsumer confidence data due Tue — risk to downside
XLBMaterialsDownSeasonal short active May–Oct. Global growth concern
XLREReal EstateDownRate-sensitive. 4.60% yield = direct headwind
XLUUtilitiesDownBond proxy. Crushed by high yield environment
📝

Step 6 — Plain-English Weekly Brief

Team Alpha Consensus Brief · W22 · Neutral-to-Cautious · Human Score −2

The market enters the week of 26 May 2026 in a technically intact but breadth-challenged position. The S&P 500 closed its eighth consecutive winning week at 7,473, still above all key moving averages, but only 57% of its member stocks are above their 200-day moving average — meaning a small number of large companies are carrying the index while most stocks are struggling. This is a structural warning sign.

The macro picture is dominated by two binary events: the Iran nuclear deal (unconfirmed — oil could spike or stay low depending on talks progress) and Thursday's PCE inflation data (the Federal Reserve's preferred inflation measure). A hot PCE print in a shortened, low-volume holiday week could cause an outsized market reaction. Our team believes none of the four AI models adequately weighted this volume-amplification dynamic.

We predict the S&P 500 will end the week slightly up (0% to +0.6%), with technology leading and real estate lagging. However, we hold this view with medium-to-low conviction. Our invalidation is clear: if SPX closes below 7,350 on any day this week, our bullish lean is wrong.

⚠️ This is an educational decision-support exercise. Nothing in this brief constitutes financial advice. All AI model outputs were reviewed and independently assessed by the team before this brief was written.

👁️

Step 7 — Week-Ahead Watchlist (26–30 May 2026)

MON 26 MAYMemorial Day — US Markets CLOSED
No US trading. Singapore and Asian markets open normally. Watch oil and geopolitical news over the long weekend — any Iran deal confirmation or collapse will move futures.
TUE 27 MAYConsumer Confidence + Earnings Catalysts
Consumer Confidence (10:00 AM ET) — a weak print adds to consumer spending concern, pressure on XLY
AutoZone (AZO), Zscaler (ZS) earnings — retail and cybersecurity sentiment reads
Watch: Does IWM follow through above 2,900? If not, last week's outperformance was a one-week event.
WED 28 MAYMajor Tech Earnings — Key for NDX
Marvell Technology (MRVL) — AI chip read-through for the semiconductor sector
Salesforce (CRM) and Snowflake (SNOW) — enterprise software and cloud spending signal
New Home Sales — housing market health under 4.60% yields
Watch: Does NDX breadth improve? If tech earns well, breadth could expand back toward 50%.
THU 29 MAY⚠️ PCE INFLATION + GDP — SWING EVENT OF THE WEEK
PCE Inflation (8:30 AM ET) — Fed's preferred measure. ≥2.8% YoY = yields spike, stocks sell off. ≤2.5% = yields ease, rally continues
GDP 2nd Estimate Q1 2026 — confirms or revises economic growth picture
Initial Jobless Claims + Durable Goods — labour and manufacturing health
Dell (DELL), Dollar Tree (DLTR), Costco (COST) earnings — consumer and enterprise demand
Holiday week + PCE = low volume amplification. Expect larger-than-normal price swings on this data.
FRI 30 MAYChicago PMI — End of Week
Chicago PMI — manufacturing activity indicator
Month-end positioning — fund managers rebalance at end of month, can create buying/selling pressure independent of news
Pull Finviz 1W + Yahoo Sectors 5D after 4PM ET. Record actuals for SPX, NDX, IWM and all 11 sector ETFs. Commit to GitHub.
Invalidation Conditions — What Would Make This Prediction Wrong
❌ PCE ≥ 2.8% YoY → yields spike → SPX sells below 7,350 → call flips Bearish
❌ Iran talks collapse → oil spikes above $68 → inflation fear returns → yields rise
❌ SPX closes below 7,350 (21 EMA + trendline) → technical breakdown confirmed
❌ New Fed Chair Warsh delivers hawkish speech → rate-cut odds fall further
📓

Step 8 — Learning Log Entry

R10 · QA & Learning Log
What did we predict last week? (W21 — first sprint, no prior prediction to score)
Week 1 was our first sprint — no prediction was filed as we were still setting up the GitHub repository and learning the workflow. This is Week 2: our first live prediction. Calibration score for W22 will be recorded after Friday's close.
What surprised us in last week's data?
Two things surprised us. First, IWM outperforming by 2.7% when yields were elevated was unexpected — we learned that IWM is sensitive not just to yields but to risk-appetite flows, and the Iran deal optimism created a specific catalyst. Second, XLE leading all sectors despite oil falling −5.7% was counterintuitive. We now understand that energy stocks can rally on geopolitical positioning even when the commodity price falls.
What was our team's key human insight this week?
The volume-amplification effect of a PCE release into a holiday-shortened week. None of the four AI models flagged this. We noticed it independently when R5 pointed out that low-volume Thursdays see exaggerated price moves on data releases. This is the kind of contextual observation that only comes from thinking about the specific week, not just applying patterns.
What will we do differently next sprint?
We will check trading volume context earlier in our Macro Agent analysis. Holiday weeks, OPEX weeks, and end-of-quarter weeks all affect how data is absorbed. We are adding a "volume context" line to the Macro Agent output template going forward.

GitHub evidence checklist — all boxes ticked before Monday class:
prediction_2026-W22_GroupA.md committed Sat 21:47 SGT
evidence/finviz_1W_2026-W22_Sat.png — Finviz screenshot
evidence/yahoo_sectors_5D_2026-W22_Sat.png — Yahoo sectors screenshot
evidence/charts_2026-W22/ — SPX, NDX, IWM annotated charts
evidence/llm_responses_2026-W22/ — all 4 raw LLM outputs
almanac_agent_2026-W22.md — Almanac output
macro_agent_2026-W22.md — Macro/News output
technical_agent_2026-W22.md — Technical output
human_score_2026-W22.md — Human Score + override paragraph
learning_log_2026-W22.md — Learning log entry
✓ Release tag vW22 created
✓ README updated with sprint status