Earnings Surprise Drift in the UK: Both Sides Active, Miss Side Leads

UK earnings beats produce +1.13% cumulative abnormal return at T+63 vs the FTSE 100. Misses produce -1.01%. The Q5-Q1 spread of +3.19% has real contributions from both tails. The UK PEAD signal is miss-weighted but no longer a pure miss-avoidance story. Q5 biggest beats produce +1.83% at T+63, which is statistically significant and practically meaningful.

Contents

1. Method
2. The Strategy
3. What We Found
4. Positive vs Negative Surprise Drift
5. Quintile Analysis at T+63
6. UK in Global Context
7. When It Works and When It Struggles
8. Run It Yourself
9. Limitations
10. Part of a Series
11. References

Data: FMP financial data warehouse, 2000–2025. Updated March 2026.

Method

The Strategy

Post-Earnings Announcement Drift (PEAD) is one of the most replicated anomalies in financial markets. Ball and Brown (1968) first documented that stocks continue drifting in the direction of their earnings surprise for weeks after announcement. Bernard and Thomas (1989) confirmed the drift persists for up to 60 trading days. Foster, Olsen, and Shevlin (1984) extended the analysis across different earnings windows.

In the US, both sides of the drift are meaningful but asymmetric: misses drift further (-2.00% at T+63) than beats (+0.24%). Measured against the FTSE 100, the UK shows a more balanced picture than a US-listed proxy benchmark suggested. Both sides produce drift, with misses leading.

What We Found

Positive vs Negative Surprise Drift

The UK beat rate is 44.3%. More companies miss than beat. Positive surprises drift up through T+21 (+1.49%), then settle at +1.13% by T+63. The positive drift is real and sustained vs the FTSE 100.

The negative surprise pattern is uneven. Misses barely drift in the first 21 days (-0.27% at T+1, briefly positive at T+21), then accelerate to -1.01% by T+63. The miss-side drift is late and smaller in magnitude than earlier analysis using a US-listed proxy benchmark suggested.

Quintile Analysis at T+63

The Q5-Q1 spread is +3.19% at T+63. Q5 (t=4.8) and Q1 (t=-3.3) both clear significance thresholds. Q5's +1.83% is a meaningful long-side signal, more actionable than the prior EWU-benchmark analysis suggested.

Q4 (+0.91%) also produces positive drift, which is a different picture from the old analysis where Q4 was near zero. The distribution now has a cleaner positive slope from Q1 through Q5.

UK in Global Context

Against local benchmarks, the UK shows stronger positive surprise drift than the US (+1.13% vs +0.24%) but weaker miss-side drift (-1.01% vs -2.00%). The UK and US have very different beat rates (44.3% vs 61.9%), which partly explains why UK beats carry more information: a 44% beat rate means each individual beat is less expected and more significant.

When It Works and When It Struggles

The UK supports both sides of a PEAD strategy vs FTSE. Q5 beats produce +1.83% over 63 days. Q1 misses produce -1.36%. The miss-side drift is late-loading: misses are nearly flat through T+21 before accelerating to -1.01% for the category average.

For a short-side implementation, the full 63-day holding period is important. The miss-side move is concentrated in the back half of the window. A shorter holding period would miss most of the edge.

UK companies tend to report results less frequently than US companies, with many on semi-annual or irregular reporting schedules. Lower reporting frequency can affect the T+63 window, which may overlap with subsequent reporting for some stocks.

Run It Yourself

python3 earnings-surprise/screen.py --preset uk

-- Recent earnings surprises on LSE
WITH deduped AS (
  SELECT
    es.symbol,
    es.date,
    es.epsActual,
    es.epsEstimated,
    (es.epsActual - es.epsEstimated) / NULLIF(ABS(es.epsEstimated), 0) AS std_surprise,
    ROW_NUMBER() OVER (PARTITION BY es.symbol, es.date ORDER BY es.lastUpdated DESC) AS rn
  FROM earnings_surprises es
  JOIN profile p ON es.symbol = p.symbol
  WHERE p.exchange = 'LSE'
    AND p.isActivelyTrading = true
    AND es.date >= CURRENT_DATE - INTERVAL '90 days'
    AND ABS(es.epsEstimated) > 0.01
)
SELECT
  symbol,
  date,
  epsActual,
  epsEstimated,
  ROUND(std_surprise * 100, 1) AS surprise_pct
FROM deduped
WHERE rn = 1
  AND ABS(std_surprise) > 0.10
ORDER BY date DESC, std_surprise ASC
LIMIT 50

Run this query on Ceta Research →

Limitations

13,071 events is a solid sample. Q5 and Q1 each have roughly 2,580–2,630 events, which is adequate for statistical analysis but smaller than equivalent quintiles for the US or Japan.

UK reporting calendars are less standardized than US quarterly reporting. A portion of UK companies report on a six-month cycle, which means the T+63 window can overlap with subsequent earnings for some companies. This could either amplify or dampen the measured drift depending on whether subsequent results reinforce the initial surprise.

Short-side PEAD strategies in the UK require access to stock borrow and face borrowing costs. The measured -1.36% Q1 drift at T+63 is gross of borrowing costs, which can run 1–3% annually for smaller LSE names.

Part of a Series

• PEAD Across 14 Global Exchanges: The Drift Is Universal
• Earnings Surprise Drift on US Stocks: 170,000 Events, 26 Years

References

• Ball, R. & Brown, P. (1968). An empirical evaluation of accounting income numbers. Journal of Accounting Research.
• Bernard, V. & Thomas, J. (1989). Post-earnings-announcement drift: Delayed price response or risk premium? Journal of Accounting Research.
• Foster, G., Olsen, C. & Shevlin, T. (1984). Earnings releases, anomalies, and the behavior of security returns. The Accounting Review.

Data: Ceta Research, FMP financial data warehouse