Research
The Narrative Factor: A Systematic Approach to Capturing Narrative Alpha from Public Discourse
Date Written: April 30, 2026
Abstract:
Market-moving narratives drive equity returns yet remain largely absent from systematic factor models. This paper introduces a narrative factor built from ForecastOS Hivemind, which quantifies company-level exposures to 14 macro narratives spanning geopolitics, technology, and monetary policy. The composite factor dynamically weights active narratives – those within 95% of their trailing six-month discussion high – by their share of total discussion volume, then standardizes cross-sectionally within industry (and subindustry) groups. Tested in a long-short portfolio of the top 500 U.S. equities from January 2020 through April 2026, the raw-signal industry-neutral specification achieves a 1.01x information ratio (6.62% excess return, 9.89% maximum drawdown); a subindustry-neutral variant achieves 0.86x (4.36% excess return, 6.74% maximum drawdown). Pre-orthogonalizing the narrative signal against momentum, value, quality, leverage, and beta (cross-sectional residualization, then top/bottom decile construction) lifts information ratios to 1.95x (industry-neutral) and 1.49x (sub-industry-neutral) – roughly doubling risk-adjusted performance – while cutting maximum drawdown from 9.89% to 4.01% (industry) and from 6.74% to 3.51% (sub-industry). Both raw and factor-neutralized portfolios achieve a positive IR in every calendar year tested. A 12-minus-1-month momentum benchmark – implemented with a monthly (21 trading day) full-reset rebalance rather than constrained daily turnover – delivers inferior risk-adjusted performance for industry / subindustry neutral portfolios (0.39x / 0.35x raw; 0.63x / 0.61x factor-neutralized) with drawdowns approaching 40% raw (~21% factor-neutralized). Cross-sectional correlation between the factors is low (average Pearson: 0.05), and zero by construction for the factor-neutralized narrative. A Fama-MacBeth cross-sectional regression reinforces this at the signal level: the narrative characteristic produces a t-statistic of 2.92 (industry-neutral) after controlling for momentum, value, quality, leverage, beta, and industry effects, clearing the conventional significance bar and confirming the signal prices the cross-section independent of portfolio construction. An equal-weight blend of raw narrative and raw momentum halves momentum’s max drawdown while achieving a 0.80x information ratio. The narrative factor is robust to activation parameter variation, delivering a similarly positive IR across all 9 combinations of threshold (92.5-97.5%) and lookback windows (120-240 days) tested.
Keywords: Asset Pricing, Factor Investing, Narrative Factor, Narrative Economics, Thematic Investing, Alternative Data, Natural Language Processing, Alpha Generation, Momentum, Market Neutral, Cross-Sectional Returns