SGG Research - fact sheet
Edition: 2026-09-29

Organization
SGG Research

Research focus
Alternative data factors for US equities, derived from structured earnings-call observations

ECPND
Earnings Call Participation Network and Dynamics: structured participation history across companies and dates

ECQDI
Earnings Call Quantitative Dynamics and Intensity: quantitative patterns in external analyst contributions

Delivery
Authenticated API access with timestamped, versioned score records; hourly checks and updates on change

Evaluation
Public whitepapers and a free research package with two years of daily historical scores, ending eight weeks before the package date

Purpose
Data analytics and independent research; not financial or investment advice

About SGG Research
SGG Research develops alternative data factors for US equity research. Its work examines who participates in earnings calls, how connections evolve across companies, and the quantitative content of external analyst contributions. SGG Research delivers versioned factor scores, historical datasets and documented studies for independent evaluation in customers' own models and workflows. Its products are data analytics and research services, not financial advice.

Historical ECPND study
Buy & hold versus Qlib / LightGBM, 10 bp per executed trade.
Formations: 2022-01-10 to 2026-09-14; prices through 2026-09-18.
3 months: +17 bp; 95% interval -13 to +47 bp; 232 completed formations.
6 months: +54 bp; 95% interval +13 to +99 bp; 219 completed formations.
12 months: +107 bp; 95% interval -5 to +218 bp; 193 completed formations.

Mean paired return differences after the stated 10 bp trading costs, averaged across completed weekly formations and four fixed model seeds. Weekly holdings overlap. The six-month 95% block-bootstrap interval is above zero; the three- and twelve-month intervals include zero. These are SGG Research's historical calculations, not independently audited results, annualized alpha or live performance. See the ECPND whitepaper for timing, universe, selection and execution assumptions.
https://sggresearch.com/whitepaper/ecpnd
