← Back to scans

Will there be a recession in 2027? — Yes

KXRECSSNBER-27 · Economics · 2026-05-13
37%
Agent
42%
Market Price
-5.0%
Edge
40%
Confidence
Volume: 27,475
Spread: 3.0c
Days to resolution: 628
Markets in event: 1
Final Rationale
My independent estimate of 31% balanced a ~20-25% historical base rate for two consecutive negative quarters in a 5-quarter window against tariff-induced supply shock risk and offsetting Fed easing/fiscal stimulus. I PARTIALLY ACCEPT the critique that I undercounted the novel tariff regime's stagflation risk and that my sub-question decomposition was overlapping rather than independent paths — adjusting up ~6pp toward 37%. I REJECT the framing that the 2022-23 yield curve signal still carries full weight (the typical 12-24 month lag has elapsed without recession, which is genuine evidence, not the never-happened fallacy). The market at 42% likely embeds additional tariff-uncertainty premium and possibly some 'recession-hedging' demand; I remain 5pp below it because Fed easing and large fiscal deficits are concrete offsets the market may discount.
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
Re-scan Context
This market has been scanned before. Previous predictions:
DatePredictedMarket PriceConfidence
2026-05-05 32% 38% 40%
2026-04-27 31% 34% 35%
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 the US economy already be in contraction or recession by Q4 2026, making consecutive negative GDP quarters extending into 2027 more likely? (w=0.30)
  2. Will leading macroeconomic indicators (yield curve, unemployment, consumer sentiment, PMI) signal recession risk high enough to predict two consecutive quarters of negative GDP growth in 2027? (w=0.35)
  3. Will current fiscal and monetary policy conditions (tariffs, Fed stance, government spending) be sufficiently contractionary to cause two consecutive negative GDP quarters by end of 2027? (w=0.35)
Planner reasoning
This question uses a technical BEA definition of recession (two consecutive quarters of negative GDP growth in Q4 2026 through Q4 2027), not the NBER definition. This distinction matters because the NBER considers multiple indicators while this market uses the simpler two-quarter rule. Reference class: post-WWII US recessions occur roughly 20-25% of years. The current environment (May 2026) features significant tariff shocks, a cautious Fed easing cycle, a yield curve that inverted in 2022-2023 with the typical 12-24 month lag already having largely passed, and fiscal spending that could offset contraction. Key causal mechanisms include tariff-driven supply shocks suppressing real output, consumer confidence feeding into spending, and labor market dynamics as leading indicators. Temporal analysis: Q4 2026 GDP won't be reported until late January/February 2027; Q1 2027 advance estimate comes ~late April 2027. For YES, we need two consecutive negative quarters within the Q4 2026 to Q4 2027 window. The most likely path is Q4 2026 negative plus Q1 2027 negative, which would be confirmed by May 2027, well before the January 2028 resolution. Alternatively Q1+Q2 2027 would be confirmed by October 2027. The tariff shock is a novel large supply-side disruption that could either cause stagflation or outright contraction depending on Fed response and demand elasticity.
2. Research Parallel tool calls · legacy v2
ToolStatusTimeItemsSummary
kalshi_data OK 1.9s -
kalshi_orderbook OK 0.2s -
fred_data OK 1.4s -
article_search OK 0.8s -
web_search OK 39.1s -
wikipedia_lookup OK 1.9s -
code_execution OK 0.0s -
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: 31% (40% confidence)
base rate
30%
40% conf
evidence driven
30%
40% conf
contrarian
33%
40% conf
Spread
3pp
Low disagreement
sq1: Will the US economy already be in contraction or recession by Q4 2026?
25%
Base rate: in any given quarter, US GDP is negative ~15-20% of the time post-WWII. As of May 2026, the economy has absorbed significant tariff shocks but no confirmed recession yet. The Q4 2026 reading won't be known until early 2027. Tariff drag and supply-side disruptions push UP by ~5-8%. Fed easing cycle and fiscal support push DOWN by ~3%. Net estimate ~25%.
sq2: Will leading indicators signal recession risk high enough to predict two consecutive negative GDP quarters in the window?
30%
Base rate for two consecutive negative quarters in a specific 5-quarter window: ~20-25% historically. Yield curve inverted in 2022-23; typical 12-24 month lag has mostly passed without recession, which actually weakens the signal (DOWN ~3%). Tariff shock is a novel supply-side disruption raising stagflation risk (UP ~5%). Labor market still relatively firm based on prior context, pushing DOWN ~2%. Net ~30%.
sq3: Will fiscal/monetary policy be sufficiently contractionary to cause two consecutive negative quarters by end 2027?
32%
Tariffs are a meaningful negative supply shock that suppresses real GDP directly (imports subtract less but real output can fall). Fed is in cautious easing mode, which is mildly supportive (DOWN ~3%). Large fiscal deficits remain stimulative (DOWN ~3%). However, tariff magnitude and persistence is the novel factor pushing UP ~8-10% above the ~22% base rate. Net ~32%.
Show full reasoning trace
base rate: Post-WWII US recessions (two consecutive negative quarters) occur in roughly 20-25% of any given 5-quarter window. The Q4 2026 - Q4 2027 window has 5 quarters, giving 4 possible consecutive pairs.
evidence updates: Tariff shock and supply-side disruption push UP modestly (~5-8pp). Fed easing cycle, ongoing fiscal stimulus, and the fact that the 2022-23 yield curve inversion's typical lag has passed without recession push DOWN slightly. The technical BEA definition (vs NBER) makes it slightly easier to trigger.
combination method: Weighted average across three sub-questions with adjustment for correlation since recessionary conditions tend to manifest together.
final: My estimate of ~30% sits modestly above the historical base rate of 20-25%, reflecting elevated but not dominant recession risk from tariff shocks balanced against supportive Fed/fiscal policy. Consistent with my prior forecasts of 31-32%.
ensemble: {'ensemble_count': 3, 'perspectives': {'base_rate': {'p_yes': 0.3, 'confidence': 0.4}, 'evidence_driven': {'p_yes': 0.3, 'confidence': 0.4}, 'contrarian': {'p_yes': 0.33, 'confidence': 0.4}}, 'spread': 0.03, 'individual_p_yes': {'base_rate': 0.3, 'evidence_driven': 0.3, 'contrarian': 0.33}}
5. Devil's Advocate Sonnet · legacy v2 Market price revealed
Reasoning Flaw Missing Info
Challenges
  1. The sub-question decomposition is poorly structured: sq1, sq2, and sq3 are highly overlapping and not independent paths to a recession. Averaging them doesn't make mathematical sense — they're three different framings of the same question. A cleaner decomposition would be: P(recession starts in 2027) = P(already in recession entering 2027) + P(recession starts during 2027 | not already in one) * P(not already in one).
  2. The base rate calculation appears inconsistent. The forecaster cites '20-25% for any 5-quarter window' but the question is about a recession occurring *in 2027* specifically, which has been historically about 15-20% (roughly 1 recession per 6-7 years). However, if defining the window as Q4 2026 - Q4 2027, the base rate should account for overlapping windows correctly.
  3. The reasoning dismisses the 2022-23 yield curve inversion signal as 'weakened because lag has passed' — but this ignores that the inversion was historically deep and long, and recessions following such inversions have sometimes occurred 24-30+ months later. This 'never happened yet so won't happen' framing borders on the never-happened fallacy in reverse.
  4. Evidence direction balance shows '0 UP, 0 DOWN, 0 NEUTRAL' — meaning no concrete evidence was actually catalogued, yet the forecaster makes specific quantified adjustments (e.g., '+5-8pp from tariffs'). These adjustments are essentially intuition dressed as analysis.
  5. Tariff shock magnitude is treated as a modest +5-10pp adjustment, but if tariffs are genuinely a 'novel supply-side disruption raising stagflation risk' as stated, this could warrant a larger upward adjustment. The forecaster seems to undercount the magnitude of their own identified risk factor.
  6. Confidence of 0.4 with 628 days to resolution is reasonable, but the forecast may be anchoring too heavily on base rates given the explicitly stated novel tariff regime.
Suggested adjustment: +5pp
The decomposition is structurally flawed (overlapping sub-questions averaged together) and the tariff shock — explicitly identified as novel and significant — appears under-weighted relative to the forecaster's own qualitative description. A modest upward adjustment to ~36% better reflects the stated evidence. This is NOT a recommendation to match the market; it's a correction for the forecaster apparently understating their own identified risk factors.
Market comparison: Forecaster: 31%, Market: 42%. The 11pp divergence is meaningful but not extreme. With 628 days to resolution, structural uncertainty is high and the market premium likely reflects tariff-regime uncertainty that the forecaster identifies but may underweight. The divergence is partially justified (forecaster correctly notes Fed easing and fiscal support as offsets), but the forecaster's own reasoning about novel tariff risks suggests they should be somewhat higher than 31%.
6. Aggregator Opus · final calibrated forecast
37% (40% confidence)
My independent estimate of 31% balanced a ~20-25% historical base rate for two consecutive negative quarters in a 5-quarter window against tariff-induced supply shock risk and offsetting Fed easing/fiscal stimulus. I PARTIALLY ACCEPT the critique that I undercounted the novel tariff regime's stagflation risk and that my sub-question decomposition was overlapping rather than independent paths — adjusting up ~6pp toward 37%. I REJECT the framing that the 2022-23 yield curve signal still carries full weight (the typical 12-24 month lag has elapsed without recession, which is genuine evidence, not the never-happened fallacy). The market at 42% likely embeds additional tariff-uncertainty premium and possibly some 'recession-hedging' demand; I remain 5pp below it because Fed easing and large fiscal deficits are concrete offsets the market may discount.