Research tools for long/short equity
Macro prediction down to the industry level, built on a methodology of self-defined industry groups. Machine-learning-scored insider buys. Accounting-anomaly flags from annual report footnotes. One purpose: cut the front end of the research process.
01 — The problem
Academic economics does not generate alpha
Macroeconomic modeling is difficult to begin with, but it is made nearly impossible by relying on bad economic theory and data. Standard economic theories and metrics are designed to justify increased government spending, not to help understand economic conditions. Because headline data is engineered for policy, it gives portfolio managers no actionable edge.
Corporate insiders provide superior economic insight. Insiders see real-time order books, inventory backlogs, and supply chain bottlenecks long before they show up in government statistics. While standard economic metrics lag, insider signals look forward, with clustered buys leading corporate turnarounds by three to twelve months.
02 — In practice
Semiconductors, called both ways
When run historically, the model’s adjusted signal goes short in January 2022 ahead of the drawdown. It flips long in January 2024, and signals long again in mid-2025.
The lower panel shows why: the composition of insider buying signals turns before the industry does. This adjusted score is calculated for each industry, and industry group.
03 — The map
The macro regime, driven by aggregated company signals
Bottom-up insider transactions are aggregated into proprietary industry groups. These signals adjust against one another based on their position around the quadrant map (below, right).
The resulting data forms a complete top-down picture. The historical macroeconomic regime and its forward path are predicted entirely by corporate operator behavior.
04 — Access
What’s on the platform
Subscription includes the macroeconomic dashboard, scored insider buys in large-capitalization companies, and year-over-year risk-factor changes across coverage. Data on the site is generalized by design.
Arms-length bespoke research is available to a limited number of institutional clients.