Cross-Asset Signal Discovery: Initial Findings

12A: Price Signals vs Fundamental Outcomes

How to read this section: We test whether three price-based signals — 12-month momentum (trailing stock return), realized volatility (annualized standard deviation of daily returns), and relative strength (stock return minus S&P 500 return) — predict next-quarter fundamental outcomes: revenue growth, operating margin change, and ROE change (all year-over-year to remove seasonality). Each cell shows the Pearson correlation (r) between signal at quarter Q and outcome at quarter Q+1. Values closer to +1 or −1 indicate stronger predictive relationships. “n” is the number of paired observations.

Across the analyzed company, Berkshire Hathaway Inc. (BRK-B), our examination of price signals against future fundamental outcomes from 2015Q1 to 2025Q4 reveals a general absence of strong or notable predictive relationships. Despite observing some statistically significant p-values for weak correlations, no price signal achieved an absolute correlation coefficient of 0.4 or higher, indicating that price movements explain very little variance in future fundamental performance for this entity. The analysis did not uncover any consistent cross-company predictive signals.

Berkshire Hathaway Inc. (BRK-B) 44 quarters | 2015Q1 to 2025Q4

Signal \ Outcome	Revenue Growth	Margin Change	ROE Change
12M Momentum	-0.21 n=40 weak	-0.13 n=40 weak	-0.39 n=40 weak
Realized Volatility	-0.14 n=40 weak	-0.21 n=40 weak	0.37 n=40 weak
Relative Strength	0.06 n=40 weak	0.02 n=40 weak	-0.14 n=40 weak

Strongest: No notable signals found

For Berkshire Hathaway Inc. (BRK-B), analysis over 40 quarterly observations from 2015Q1 to 2025Q4 indicates no notable or strong predictive signals between the examined price metrics and future fundamental outcomes. While certain relationships show statistical significance (p < 0.05), their correlation coefficients remain below the 0.4 threshold for 'notable' strength. Specifically, 12-month momentum exhibits a weak inverse correlation with ROE Change (r = -0.391, p = 0.013, n = 40), suggesting that stronger past price performance for BRK-B has been weakly associated with a subsequent decline in return on equity. Similarly, realized volatility displays a weak positive correlation with ROE Change (r = 0.368, p = 0.019, n = 40), implying a minor tendency for higher past volatility to precede an increase in ROE. All other observed correlations, including those involving revenue growth and margin change, were weak and not statistically significant (p > 0.05).

BRK-B - Correlation Heatmap

Cross-Company Patterns

No consistent cross-company predictive signals found

12B: Institutional Flow vs Price Impact

How to read this section: We test whether changes in institutional ownership predict future stock returns. Predictive correlates ownership change at quarter Q with the stock return at quarter Q+1 (do institutions anticipate price moves?). Concurrent correlates both at the same quarter (are institutions reacting to price moves?). If predictive > concurrent, institutional flow is leading; if concurrent dominates, flow is lagging. Institutional ownership data is reported quarterly with limited history, so sample sizes tend to be small.

Analysis of institutional flow data against price impact reveals varied dynamics across companies. For Berkshire Hathaway Inc. (BRK-B), institutional flow appears to be a strong predictive signal for subsequent price movements, with a notable lead over concurrent relationships. This suggests that the aggregate activity of institutional investors in BRK-B may reflect informational advantages or forward-looking positioning that anticipates future price action, rather than merely reacting to existing trends.

Berkshire Hathaway Inc. (BRK-B) leading

Metric	Correlation	p-value	n	Significance
Predictive (flow Q → return Q+1)	0.8666	0.0573	5	strong
Concurrent (flow Q ↔ return Q)	-0.5233	0.2867	6	notable

Predictive |r|=0.87 exceeds concurrent |r|=0.52 by >0.1

Institutional flow for Berkshire Hathaway Inc. (BRK-B) is classified as leading. The predictive correlation between institutional flow and subsequent price impact is strong, evidenced by an r-value of 0.8666 over 5 observations (n=5). While this correlation approaches conventional statistical significance (p=0.0573), the limited sample size warrants cautious interpretation. In contrast, the concurrent correlation between institutional flow and immediate price impact is notably negative at r=-0.5233 over 6 observations (n=6), though it is not statistically significant (p=0.2867). The substantially higher magnitude of the predictive correlation compared to the concurrent correlation, and its positive direction, supports the classification that institutional flow for BRK-B tends to precede price movements.

BRK-B - Ownership Change vs Next-Quarter Return

12C: Earnings Surprise Patterns

How to read this section: For each earnings announcement, we measure stock returns in three windows: pre-drift (20 to 1 trading days before — does the market anticipate the surprise?), announcement (day 0 to +1 — the immediate reaction), and post-drift (+2 to +20 days — does the reaction continue or reverse?). Events are classified as positive (>2% EPS surprise), negative (<−2%), or inline. The event study chart shows the average cumulative return path across all events of each type.

This analysis examines the earnings surprise patterns for Berkshire Hathaway Inc. (BRK-B), focusing on historical beat rates, consistency, and associated stock price movements around earnings announcements. BRK-B exhibits a high earnings beat rate, but the overall sample size of events is very limited, necessitating caution in drawing definitive conclusions. A notable inverse relationship is observed between pre-announcement price drift and the subsequent earnings surprise direction, suggesting a complex dynamic prior to official reports. Significant post-announcement drift is evident following positive surprises, indicating a delayed market assimilation of favorable news.

Berkshire Hathaway Inc. (BRK-B) 6 events

Beat Rate

66.7%

Avg EPS Surprise

30.18%

Consecutive Beats

2

Surprise Trend

widening

Direction	Events	Avg Pre-drift [-20,-1]	Avg Announcement [0,+1]	Avg Post-drift [+2,+20]
positive	4	-1.81%	0.21%	6.54%
negative	2	1.38%	0.10%	1.02%

Pre-drift return predicts surprise direction (r=-0.4968)

Berkshire Hathaway Inc. (BRK-B) has a strong earnings beat rate of 66.7% across 6 observed events, with an average EPS surprise of 30.18%. The company shows a recent consistency with two consecutive beats and no consecutive misses. However, the average revenue surprise is slightly negative at -1.19%. The surprise trend is noted as 'widening,' which suggests increasing variability in the magnitude of earnings surprises over time. A notable inverse relationship exists between pre-announcement price drift and the subsequent earnings surprise, with a correlation of r=-0.4968 (n=6). This implies that negative pre-announcement drift (-1.81% over 4 positive surprise events) tends to precede positive earnings surprises, while positive pre-announcement drift (1.38% over 2 negative surprise events) precedes negative surprises. Announcement day reactions are minimal for both positive (0.21%) and negative (0.1%) surprises. Post-announcement, a substantial positive drift of 6.54% is observed following positive surprises (4 events), indicating a delayed market reaction. Interestingly, a modest positive drift of 1.02% is also noted after negative surprises (2 events), though this is based on a very limited number of observations.

BRK-B - Earnings Event Study [-20, +20] Days

12D: Multi-Signal Integration

Our analysis integrates multiple predictive signals to assess underlying market patterns for Berkshire Hathaway Inc. (BRK-B). This approach moves beyond isolated metrics to identify converging or diverging indicators of future performance. While some companies exhibit broad predictability across various signal types, others show highly specific drivers. This assessment delineates the specific signal strengths and limitations for BRK-B, providing a nuanced view of its systematic predictability.

Company	Price-Fundamental Signals	Institutional Predictive	Pre-drift Predictive	Earnings Consistency	Signal Coverage	Data Quality
BRK-B	0	Yes	Yes	mixed	moderate	strong

BRK-B

For Berkshire Hathaway Inc. (BRK-B), the analysis reveals a strong predictive signal from institutional activity, specifically showing a leading correlation of r=0.8666. This indicates that institutional positioning significantly anticipates future price movements. Additionally, pre-drift predictive signals are present, further suggesting identifiable patterns around corporate events or information dissemination. Data quality for BRK-B signals is strong, supporting the reliability of these findings, though overall signal coverage is moderate. The absence of notable or strong price-fundamental signals suggests that traditional valuation ratios or trend-following from price alone do not exhibit strong predictive power for BRK-B. Earnings consistency is mixed (beat rate: 67%), which might explain the lack of strong price-fundamental signals if earnings surprises are frequent or unpredictable. Despite the mixed earnings consistency and lack of strong price-fundamental signals, the strong institutional and pre-drift signals converge to suggest that BRK-B exhibits a notable degree of pattern predictability, primarily driven by informed institutional flows and event-based dynamics.

Signal Coverage Heatmap

12E: Signal Discovery Summary

This analysis identifies specific predictive signals within Berkshire Hathaway Inc. (BRK-B), while noting a lack of consistent cross-company patterns across the broader universe examined. For BRK-B, institutional flow exhibits a strong leading correlation with price, measured at r=0.8666 over 5 quarterly observations. Additionally, pre-drift returns prior to earnings announcements show a notable negative correlation (r=-0.4968) with subsequent earnings surprises, suggesting that negative price action preceding earnings may anticipate positive surprises. It is crucial to acknowledge that while these correlations are statistically significant within their respective sample sizes, the limited number of observations (e.g., n=5 for institutional flow) necessitates cautious interpretation. The absence of broadly applicable cross-company signals suggests that predictive relationships are often idiosyncratic.

Signal Predictability Rankings

BRK-B moderate

BRK-B shows a strong, but very small sample, signal of institutional flow leading price and a notable signal of pre-drift return predicting earnings surprise.

Top Signals by Company

Berkshire Hathaway Inc. (BRK-B)

Institutional flow leads price: r=0.8666, n=5

Pre-drift return predicts earnings surprise: r=-0.4968

Caveats: Correlation does not imply causation; Past predictive relationships may not persist

Monitoring Recommendations

For BRK-B, monitor institutional flow data for potential leading indicators of price movements, acknowledging the very small sample size (n=5) of the strong observed correlation (r=0.8666).

For BRK-B, observe pre-earnings price drift; a negative drift may precede positive earnings surprises, given the notable inverse correlation (r=-0.4968).

Investors should prioritize detailed, company-specific signal discovery rather than relying on generalized cross-asset patterns, as no such patterns were found in this study.

Cross-Company Patterns

No consistent cross-company predictive signals found

Key Takeaways

1. 1. Institutional flow is a strong leading indicator for BRK-B's price (r=0.8666), though based on a very limited sample size (n=5).

2. 2. Pre-drift returns for BRK-B exhibit a notable inverse correlation (r=-0.4968) with earnings surprises, suggesting a contrarian signal.

3. 3. No consistent predictive signals were found to generalize across multiple companies, emphasizing company-specific dynamics.

4. 4. The identified signals, while strong or notable, are derived from small sample sizes, which can limit their reliability and generalizability.

5. 5. Predictive relationships are subject to regime shifts and do not imply causation, requiring continuous validation.

Methodology

Signal discovery uses Pearson correlation with lagged variables. Minimum sample sizes: 8 quarterly observations for price-fundamental, 5 for institutional flow, 4 earnings events. Significance thresholds: |r| >= 0.6 (strong), |r| >= 0.4 (notable). All correlations are bivariate; multivariate relationships not tested. Quarterly fundamentals use YoY changes (pct_change(4)) to avoid seasonality. Event study uses trading days [-20, +20] around earnings announcements.

This analysis relies on Pearson correlation with lagged variables, which identifies linear relationships and does not imply causation. All correlations are bivariate; potential multivariate relationships were not explored. Sample sizes are critical: minimum 8 quarterly observations for price-fundamental relationships, 5 for institutional flow, and 4 earnings events for event studies. Correlations are categorized as 'strong' for |r| >= 0.6 and 'notable' for |r| >= 0.4. Past predictive relationships may not persist due to market regime changes or other dynamic factors. Quarterly fundamental data uses Year-over-Year changes to mitigate seasonality.