← Back to scans

Will there be a recession in 2027? — Yes

KXRECSSNBER-27 · Economics · 2026-04-27
31%
Agent
34%
Market Price
-3.0%
Edge
35%
Confidence
Volume: 12,558
Spread: 1.0c
Days to resolution: 643
Markets in event: 1
Final Rationale
My independent estimate of 27.3% was built on historical base rates (~20-25% for any 5-quarter window having two consecutive negative GDP quarters) plus an upward adjustment for the 2025 tariff shock environment. I partially accept Challenge 1 (relying on assumed context without cited evidence) and Challenge 3 (opaque combination under-weighting sq3's leading indicators at 0.40), which together justify nudging up. I reject Challenge 2's framing — the resolution criteria explicitly state two consecutive negative quarters Q4 2026-Q4 2027 per BEA, so this is a technical recession question, not NBER. Given the market at 35% likely incorporates current 2026 macro data I lack, and the forecaster's information disadvantage over a 643-day horizon, I move toward but not all the way to market — settling at 31% reflects partial deference while preserving my view that technical-recession criteria are stricter than the market may price.
Price vs. prediction
How the market moved after the agent's call. Solid blue line is the actual market price; dashed line is the agent's static forecast at $t{=}0$.
$n = 58$ follow-ups
1. Planner Opus · Fermi decomposition + tool plan
Tools chosen: kalshi_data kalshi_orderbook fred_data article_search web_search wikipedia_lookup code_execution
Sub-questions (Fermi decomposition)
  1. Will US GDP growth be negative in Q4 2026, signaling the start of a recession entering the resolution window? (w=0.25)
  2. Will US GDP growth be negative for at least two consecutive quarters within the Q4 2026 through Q4 2027 window? (w=0.40)
  3. Are current leading economic indicators consistent with a US recession occurring within the next 12-18 months? (w=0.20)
  4. Has a US recession already begun in 2025 or early 2026 that could extend into the Q4 2026 to Q4 2027 resolution window? (w=0.15)
Planner reasoning
This question uses a specific technical definition: two consecutive BEA-reported negative GDP quarters within a five-quarter window (Q4 2026 through Q4 2027). This differs from an NBER recession call, which uses broader criteria including employment and income. The key analytical steps are: (1) assess current economic trajectory given the 2025 tariff shock and trade war uncertainty; (2) evaluate leading indicators such as the yield curve inversion, initial jobless claims, consumer sentiment, and credit conditions; (3) apply historical base rates adjusted for current elevated risk; (4) check prediction market pricing as an aggregated signal. The temporal sequence for YES requires GDP to turn negative in at least one quarter starting no later than Q3 2027, with the preceding quarter also negative. Given that we are in April 2026, roughly 2-3 quarters of data will be available before the critical window opens. The tariff shock of 2025 represents a significant negative supply and demand shock that could persist into 2026-2027 depending on trade policy resolution. If no trade deals are reached and the Fed is slow to cut, the probability of two consecutive negative GDP quarters rises substantially. Reference class: post-WWII annual recession base rate is roughly 30%, but elevated uncertainty and policy shocks push conditional probability higher for this specific window.
2. Research Parallel tool calls · legacy v2
ToolStatusTimeItemsSummary
kalshi_data OK 2.1s -
kalshi_orderbook OK 0.4s -
fred_data OK 2.0s -
article_search OK 0.7s -
web_search OK 42.2s -
wikipedia_lookup OK 1.7s -
code_execution OK 0.1s -
3. Evidence Synthesis Sonnet · 0 items · legacy v2
#StrengthCredibilityDirectionSourceClaimPriced In
4. Independent Forecaster Opus · No market price · legacy v2 Did NOT see market price
Independent estimate: 27% (38% confidence)
base rate
28%
40% conf
evidence driven
26%
35% conf
contrarian
28%
40% conf
Spread
2pp
Low disagreement
sq1: Will US GDP growth be negative in Q4 2026?
22%
Base rate for any single quarter being negative GDP in post-WWII US is ~15-18% (recessions occupy ~14% of quarters historically). Context: 2025 tariff shock has elevated recession risk. By Q4 2026, either tariff effects will have largely passed through or the economy will be in active contraction. Tariff shock pushes UP by ~5-7%. Fed likely cutting rates in 2026 in response, pushing DOWN by ~2%. Net: ~22%.
sq2: Will GDP be negative for two consecutive quarters within Q4 2026 - Q4 2027?
28%
Base rate: In any rolling 5-quarter window, probability of two consecutive negative quarters historically is ~18-22% (roughly one technical recession per decade lasting 2-4 quarters). The 2025 tariff shock substantially raised recession odds for 2026-2027. However, technical recessions (2 consecutive negative quarters) are rarer than NBER recessions — 2001 didn't have two consecutive negatives, and 2022 had two consecutive negatives without NBER calling a recession. Tariff persistence and policy uncertainty push UP by ~8%. Fed easing cycle and resilient labor market push DOWN by ~3%. Final: ~28%.
sq3: Are leading indicators consistent with recession in next 12-18 months?
40%
Without specific evidence provided, I rely on context: 2025 tariff shock, ongoing trade war uncertainty, and the question framing implies elevated recession indicators. Yield curve dynamics in 2024-2025 inverted then normalized (often a recession signal). Consumer sentiment likely weakened post-tariffs. Leading indicators 'consistent with' recession is a broader standard than recession actually occurring. Estimate ~40% given elevated but not overwhelming signals.
sq4: Has a recession already begun in 2025/early 2026 extending into the window?
20%
If a recession started in 2025 due to tariff shock, it would likely be relatively short (2-4 quarters) and might end before Q4 2026. For it to 'extend into' the window with two consecutive negative quarters in Q4 2026+, it would need to be unusually prolonged or have a double-dip. Most tariff-induced recessions in modern era have been short. Base rate for ongoing recession at any given moment: ~15%. Slight elevation for current conditions: ~20%.
Show full reasoning trace
base rate: Post-WWII US recessions occur roughly once per decade. Probability of two consecutive negative GDP quarters within any specific 5-quarter window is ~20-25% historically. Technical recessions (2 consecutive negatives) are slightly rarer than NBER recessions due to noise (e.g., 2001 had no consecutive negatives despite being a recession).
evidence updates: 2025 tariff shock is a significant negative shock pushing probability up from ~22% baseline to ~28%. Fed likely easing in 2026 partially offsets. Lack of specific evidence on current GDP trajectory limits confidence in updates.
combination method: Weighted average across sub-questions, with sq2 most directly measuring the resolution criteria. Adjusted for positive correlation among sub-questions.
final: 28% probability reflects elevated-but-not-extreme recession risk for Q4 2026-Q4 2027 window, accounting for tariff shock effects and policy uncertainty while recognizing technical recession criteria are stricter than NBER calls.
ensemble: {'ensemble_count': 3, 'perspectives': {'base_rate': {'p_yes': 0.28, 'confidence': 0.4}, 'evidence_driven': {'p_yes': 0.26, 'confidence': 0.35}, 'contrarian': {'p_yes': 0.28, 'confidence': 0.4}}, 'spread': 0.02, 'individual_p_yes': {'base_rate': 0.28, 'evidence_driven': 0.26, 'contrarian': 0.28}}
5. Devil's Advocate Sonnet · legacy v2 Market price revealed
Missing Info Reasoning Flaw
Challenges
  1. The forecaster admits 'without specific evidence provided' for sq3 and largely relies on assumed context about a '2025 tariff shock' — but no actual evidence is cited in the Evidence Used section (0 UP, 0 DOWN, 0 NEUTRAL). This means the entire upward adjustment from base rates is built on assumed context rather than verified information, which should widen uncertainty rather than support a specific point estimate.
  2. The resolution criterion ambiguity is not adequately addressed. 'Recession in 2027' could be defined by NBER call, two consecutive negative quarters occurring in 2027, or a recession being ongoing during 2027. The forecaster's sq2 uses a Q4 2026 - Q4 2027 window, but the question is about 2027 specifically. If NBER-defined, the probability differs from technical recession criteria, and the forecaster doesn't commit to which standard applies.
  3. Sub-question combination is opaque. The final answer (0.273) is close to sq2 (0.28), but the reasoning trace says 'weighted average' without specifying weights, and sq3 at 0.40 and sq4 at 0.20 should pull the estimate in different directions. The combination method needs to be transparent — particularly because sq3 measures a different thing (leading indicators vs. actual recession).
  4. With 643 days until resolution, structural uncertainty should dominate, and the forecaster's confidence of 0.383 may actually be appropriate — but the ensemble spread of 0.02 across perspectives seems artificially narrow given the genuine information gaps the forecaster acknowledges.
  5. The forecaster dismisses the market signal implicitly. A liquid market at 35% incorporates information from many participants with access to current macro data the forecaster admits lacking. The 7.7% divergence isn't huge, but the forecaster's information disadvantage (no concrete 2026 macro data cited) should make them weight the market more.
Suggested adjustment: +4pp
Modest upward adjustment warranted because (1) the forecaster acknowledges lacking specific current evidence yet still applies confident downward adjustments from sq3's 0.40 reading, and (2) sq3's leading-indicator probability of 0.40 should arguably get more weight since it reflects forward-looking signals for the actual resolution window. The combination method appears to under-weight sq3. This is a reasoning flaw, not market conformity — though it happens to move slightly toward the market.
Market comparison: Forecaster: 27.3%, Market: 35.0%. The 7.7% divergence is moderate. Given the forecaster's admitted lack of specific current evidence and the long time horizon (643 days), the market likely incorporates more recent macro data. Divergence is partly justified by the forecaster's reasonable skepticism about technical recession criteria, but the magnitude of the gap suggests under-weighting of leading indicator signals.
6. Aggregator Opus · final calibrated forecast
31% (35% confidence)
My independent estimate of 27.3% was built on historical base rates (~20-25% for any 5-quarter window having two consecutive negative GDP quarters) plus an upward adjustment for the 2025 tariff shock environment. I partially accept Challenge 1 (relying on assumed context without cited evidence) and Challenge 3 (opaque combination under-weighting sq3's leading indicators at 0.40), which together justify nudging up. I reject Challenge 2's framing — the resolution criteria explicitly state two consecutive negative quarters Q4 2026-Q4 2027 per BEA, so this is a technical recession question, not NBER. Given the market at 35% likely incorporates current 2026 macro data I lack, and the forecaster's information disadvantage over a 643-day horizon, I move toward but not all the way to market — settling at 31% reflects partial deference while preserving my view that technical-recession criteria are stricter than the market may price.