The Z-Score Combo 67/33 (67% momentum, 33% BRAIN sentiment) delivers Sharpe 0.26 — the only L/S strategy that reaches statistical significance (p=0.034). It turns $10M into $15.9M over 7 years with -13.7% max drawdown — dramatically better than pure momentum's -18.8% drawdown. Meanwhile, pure BRAIN sentiment as standalone generates only Sharpe -0.67 — confirming it is NOT a standalone alpha source but a powerful momentum enhancer.
| Strategy | Ann. Ret | Sharpe | Sortino | Max DD | Win% | PF | p-val | Final |
|---|---|---|---|---|---|---|---|---|
| Pure Momentum 12-1 (L/S) | 6.9% | 0.23 | 0.28 | -18.8% | 66% | 1.7 | 0.064 | $16.12M |
| Pure BRAIN Sentiment (L/S) BRAIN | 1.2% | -0.67 | -0.98 | -12.4% | 60% | 1.2 | 0.496 | $10.86M |
| Sentiment-Confirmed Momentum (L/S) BRAIN | 5.4% | 0.08 | 0.10 | -21.2% | 59% | 1.5 | 0.154 | $14.55M |
| Sentiment-Weighted Momentum (L/S) BRAIN | 5.4% | 0.08 | 0.10 | -20.6% | 58% | 1.5 | 0.163 | $14.58M |
| Z-Score Combo 50/50 (L/S) BRAIN | 4.7% | 0.02 | 0.04 | -12.9% | 63% | 1.6 | 0.095 | $13.89M |
| Z-Score Combo 67/33 (L/S) BRAIN | 6.7% | 0.26 | 0.37 | -13.7% | 65% | 1.8 | 0.034 | $15.91M |
| Long-Only: BRAIN Sentiment Top Decile BRAIN | 8.2% | 0.18 | 0.29 | -24.8% | 57% | 1.4 | 0.193 | $17.65M |
| Long-Only: Momentum Top Decile | 12.4% | 0.32 | 0.53 | -26.2% | 58% | 1.6 | 0.115 | $23.07M |
| Equal-Weight Market | 6.9% | 0.11 | 0.17 | -31.8% | 59% | 1.4 | 0.272 | $16.15M |
L/S = Long/Short (top decile long, bottom decile short). Transaction costs: 10bps round-trip. Decile = top/bottom 10% of stocks. $5 min price filter. Monthly rebalancing.
Normalized portfolio value ($1 = starting value). All strategies include 10bps round-trip transaction costs.
Comparing the top-decile long-only implementations against equal-weight market benchmark.
| Strategy | Max Drawdown | Interpretation |
|---|---|---|
| Pure Momentum L/S | -18.8% | Vulnerable to momentum crashes (Mar 2020) |
| Combo 67/33 L/S | -13.7% | Sentiment filter reduces drawdown 27% |
| Pure BRAIN Sentiment L/S | -12.4% | Lowest drawdown but lowest returns |
| Equal-Weight Market | -31.8% | Full market exposure during COVID crash |
The 67/33 combo reduces momentum's max drawdown from -18.8% to -13.7% (27% improvement) while maintaining nearly identical returns (6.7% vs 6.9%). This is the clearest evidence of BRAIN sentiment's value — it acts as a risk filter that prevents the strategy from taking momentum positions contradicted by NLP sentiment.
| Year | Momentum L/S | BRAIN Sent. L/S | Combo 67/33 L/S | EW Market |
|---|---|---|---|---|
| 2018 | 7.8% | -0.2% | 8.0% | -1.5% |
| 2019 | 9.9% | 3.0% | 10.8% | 11.1% |
| 2020 | -5.7% | 0.6% | 3.4% | 24.2% |
| 2021 | -2.8% | -2.1% | -5.6% | 14.9% |
| 2022 | 11.7% | -3.0% | 9.1% | -0.9% |
| 2023 | 17.8% | 0.9% | 8.7% | 1.2% |
| 2024 | 14.1% | 8.9% | 17.1% | 12.9% |
| 2025 | -1.1% | 0.6% | -1.8% | -8.6% |
| Signal | 67% Momentum (z-score) + 33% BRAIN Sentiment (z-score) |
| Position Sizing | Equal-weight, top/bottom decile |
| Annualized Return | 6.7% |
| Sharpe Ratio | 0.26 |
| Sortino Ratio | 0.37 |
| Max Drawdown | -13.7% |
| Win Rate | 65% |
| Profit Factor | 1.8 |
| p-value | 0.034 |
| Best Month | 5.4% |
| Worst Month | -6.9% |
| Avg Positions | 171L / 171S |
Each month:
Momentum is the stronger standalone signal (Sharpe 0.23 vs -0.67). Giving it higher weight preserves its alpha while using sentiment to filter out momentum signals contradicted by NLP. The 67/33 blend is optimal because it captures momentum's return driver while benefiting from sentiment's risk-reduction properties.
| Use Case | Recommendation | Evidence Strength |
|---|---|---|
| Momentum overlay / risk filter | RECOMMENDED — 67/33 blend | Strong (p=0.034, 27% DD reduction) |
| Secondary signal in multi-factor model | Worth exploring at 20-33% weight | Moderate |
| Standalone L/S strategy | NOT RECOMMENDED | Negative Sharpe (-0.67) |
| Long-only stock selection | Marginal — momentum top-decile is better | Weak |
BRAIN markets its datasets to "large quantitative funds using Brain datasets as raw signals" — our results confirm this is the correct use case. The data adds value as a signal ingredient (the 33% sentiment weight in our best strategy) rather than as a standalone trading strategy. BRAIN's own validation shows quintile monotonicity on their BLMCF dataset — we find similar directional but non-monotonic patterns on the Combined Sentiment dataset, with the combination achieving the clean ordering BRAIN demonstrates.
| Universe | 1875 US equities |
| Period | 2018-01 to 2025-02 |
| Rebalancing | Monthly (last business day) |
| Initial Capital | $10M |
| Transaction Costs | 10bps round-trip |
| Position Sizing | Equal-weight within each leg |
| Decile Selection | Top/bottom 10% |
| Price Filter | $5 minimum |
| Return Caps | ±100% monthly |
| Sentiment | BRAIN Combined Sentiment (us_20170101_20250310.zip) |
| Prices | Yahoo Finance (adjusted close) |
| Signals | COMBINED_SENTIMENT, NEWS_SENTIMENT, EC_LAST_CALL_SENTIMENT, CF_LAST_10K_SENTIMENT |
Report generated by Kamba Research Platform. Past performance is not indicative of future results. This analysis is for informational purposes only.