Research in progress

Does alternative data
lead stock returns?

Wikipedia pageviews, GDELT news tone, Google Trends, and SEC filings — tracked daily across the S&P 500 and a retail-attention basket. Rigorously tested, honestly reported. Null results included.

Data through Oct 3, 2026 · Universe: 503 S&P 500 + 15 retail-attention

Accumulating history. Evaluation requires sufficient out-of-sample data. The pipeline has been running since Oct 3, 2026. Results will appear here once there is enough data to compute reliable statistics. See the power analysis for the estimated timeline.

S&P 500 constituents tracked by GICS sector (n = 503 names, as of 2026-10-03)

0 83 names Industrials 83 Financials 76 Information Technology 74 Health Care 60 Consumer Discretionary 47 Consumer Staples 33 Utilities 31 Real Estate 30 Materials 25 Communication Services 23 Energy 21
S&P 500 universe
503
names in universe across 11 GICS sectors
Retail attention basket
15
high-retail-interest names (GME, AMC, etc.)
Tickers with data
—
price series collected so far

Universe of 518 names as of 2026-10-03. Data collection starts when the daily pipeline runs. Evaluation uses only names present in the S&P 500 on the feature date (point-in-time; no look-ahead).

No look-ahead

Every record stores when we observed it and what period it describes. Features for date t may only use data before the t decision time.

Pre-registered

Hypotheses, signal definitions, evaluation metrics, and failure criteria were committed before any evaluation code ran on real data.

Failure shown honestly

Null results appear on their signal pages. A signal that doesn't work says so. The baseline always appears alongside.

Prediction ledger is immutable

Each day's predictions are written and committed before outcomes are known, with model version and data hash. No history rewriting.