Paired portfolios.
01 - FORMATIONCustom Qlib, Qlib reference forecasts and momentum share one dated universe. Both Qlib models use four seeds; momentum is one deterministic ranking.
- Weekly formation dates
- 194
- Seeds per Qlib model
- 4
A point-in-time factor capturing how informed attention shifts across companies and sectors, for quantitative research and data analytics.
Mean return difference versus the Custom Qlib / LightGBM baseline
Weekly cohorts · 40% priority rule. Selected after historical testing. Study details
Participation and recurring connections may reveal informed attention. We translate these dynamics into a systematic factor for equity research.
Three US equity rankings, each tested with and without ECPND under the same weekly portfolio rules, dates and costs.
Custom Qlib, Qlib reference forecasts and momentum share one dated universe. Both Qlib models use four seeds; momentum is one deterministic ranking.
Every ranking has buy & hold cohorts, weekly rebalanced cohorts and a continuous weekly account, with 95% equally allocated and shared execution rules.
A separate accounting implementation reproduces 27 continuous-account paths. Frozen input checks support internal reproducibility, not an external audit.
Custom Qlib buy & hold portfolios, with and without the 40% ECPND overlay. The same forecasts, execution rules and costs.
The common study tests Custom Qlib, Qlib reference forecasts and momentum across 194 weekly starting dates from January 2023. Each ranking has buy & hold and weekly rebalanced cohorts, plus continuous weekly accounts, using the same candidate universe and costs. The chart shows the Custom Qlib buy & hold comparison: +86 bp mean six-month uplift at the 40% priority rule. All three displayed intervals include zero. Every baseline is tested from 0% to 100% in five-point steps; the 40% focus was selected after historical testing. View all three matched comparisons.
Continuous accounts, the same weekly rules. The 40% rule changes annualized return by +0.75 percentage points for Custom Qlib, +0.38 points for the Qlib reference forecasts and -0.16 points for momentum. 2 of four Custom Qlib seeds and 3 of four reference-model seeds improve; momentum declines slightly. These CAGR differences measure separately funded accounts and are not annualized cohort averages. Results vary across periods, and the continuous-account intervals include zero. The reference forecasts use this common weekly protocol; the separate daily TopkDropout results remain documented in the whitepaper.
Evaluate the factor with the research package, then access the ECPND score directly via API and integrate it into your workflows and models.
2 years of daily scores
$1,850 USD / month
Limited seats
No risk - cancel anytime.
Payments processed by Paddle.com · Buyer Terms · Privacy · Refunds
Understand factor coverage, historical data and update timing, with practical guidance on API access, independent evaluation and subscriptions.
Each subscription provides authenticated API access to your selected factor across its covered US equity universe. You receive scores with publication timestamps and version identifiers, historical downloads, API documentation and integration support. Current scores are available as JSON or CSV. See the integration examples.
The service checks for changes hourly and publishes an updated score set when relevant inputs change, including new or corrected calls and newly eligible history. Otherwise, the existing set remains available. Each response identifies when the data were checked and when the scores were published. See timing and data status.
Subscribers can download a five-year historical score release for their licensed factor as compressed CSV. The free research packages contain two years of daily scores, ending eight weeks before the package release date. Each download states its exact dates and coverage; historical releases are separate from ongoing API updates. See historical data delivery.
No eligible value is available for that stock and date under the factor's coverage, history or freshness rules. Missing values appear as null in JSON and blank fields in CSV; zero is a valid score. A day without a new company call does not automatically mean a missing score. See the score definitions.
Yes. The free research package includes historical scores, study results, cohort comparisons and a worked selection example. No account or payment is required. Use the supplied data to test the factor in your own models; the whitepapers explain the study design, application rules and limitations.
The standard licence covers one legal entity with up to USD 250 million AUM. Internal use, copies and storage are permitted; data, scores and API access cannot be shared with another company, including an affiliate. Derived datasets, scores, models, reports and analytics may be used internally but may not be supplied as products or services to third parties, even if the original scores cannot be reconstructed. Each additional legal entity needs its own licence. If your AUM exceeds the limit, notify us promptly and within three calendar months at the latest, and agree an individual licence. We may request proportionate supporting evidence up to twice per rolling twelve months. See the data licence and AUM definition.
Your agreed early access price and licence scope continue while the same subscription remains uninterrupted and within its licence limits, even after the factor enters regular sale. New early access admissions are limited by the licence allocation and USD 1 billion of aggregate Licence AUM, whichever is reached first. This admission limit does not remove existing subscribers' agreed terms. New products or an AUM upgrade require a separate agreement. The service may be discontinued; unused prepaid access is then addressed under the Terms. See early access continuity.
The monthly price is billed every three months, plus applicable taxes. Subscriptions renew quarterly unless cancelled before renewal. You can cancel through your account and retain access until the end of the paid period. Cancellation stops future renewals; refunds are handled separately under the Refund Policy. See the billing terms.