How news becomes
a signal you can explore.

Search and relationship discovery identify candidates; co-occurrence is not proof of economic exposure. We review source-backed business activity, resolve aliases to company IDs and apply public-company and liquidity checks.

These screens select the current basket for historical analysis; they do not establish membership at every past date. The approved 14-company basket is followed across all 1,096 days from October 27, 2023 through October 26, 2026. Diversified operators can qualify; broad hyperscalers are excluded.

Customer demand, service delivery, capital and economics, and operating permissions organize the four narratives. Every narrative has five mechanism pairs: five beneficial statements and five adverse statements.

Statement direction is not company impact: a supply constraint may harm one business and benefit a competitor. Statements cover different projects and companies while remaining specific enough to test against an atomic event.

Balanced specifications use six retrieval queries per statement to cover different expressions of the mechanism. Shared passage identities prevent overlapping searches from becoming unrelated extraction inputs. Retrieval finds candidates; it does not establish statement membership.

The extractor requires a named company and a causal effect. Resolution links it to the basket. Pure macro commentary without an attributable company effect does not enter the impact dataset. A document can contain several distinct events.

Every claim is assessed against all statements in its narrative, regardless of which query found it. An event can receive several memberships. When it concerns the narrative’s subject but no statement is a perfect fit, the closest statement is retained. Mechanism labels do not veto a contextual match. Classification is automated and can be wrong; the source remains available for review.

Freshness compares the encoded event with the source’s publication timestamp; there is no single age cutoff. Changed approvals, milestones or commercial terms may be new. Historical background receives zero weight and is excluded from the eligible registry. Uncertain freshness retains weight 1 in the service—it does not mean verified new.

Freshness asks whether information is new. Hashing asks whether the exact triplet is already known.

The reusable service multiplies these five factors. Historical background has F = 0; new, materially updated and uncertain records have F = 1. Direction comes from the company-effect predicate, not the statement’s label.

Attention retains one triplet per statement, company and document using source order. Local clusters normalize text to measure frequency. Density uses all processed statement documents, including those without retained triplets; percentile ties receive an average rank. This normalization is not the final event hash.

These are evidence weights, not expected returns or probabilities. The website uses frozen, precomputed historical scores and series; current service settings are not applied retroactively. Comparisons require pinned scoring provenance.

Impact is attributed to the earliest eligible publication day. First-day retained observation scores are averaged; later matching evidence does not revise that contribution. Evidence keeps its actual dates and source links.

The theme index counts shared exact events once across narratives while preserving memberships. Different wording can describe the same real-world deal and retain separate scores. Visual event groups bring those descriptions together in the table without changing the scoring dataset. A group can contain both benefit and harm assessments; neither is discarded. Repeated wording and reviewed wording variants share one entry, preserving all original assessments and sources. The displayed score averages the unique triplets, first averaging each triplet’s original assessments. This display average does not change the index.

The daily formula applies when there are eligible events; no-event days contribute zero. Robust calibration caps extremes. Company evidence is averaged across 60 calendar days, then combined across the basket. Early values remain blank during warm-up. A decline may reflect old positive events leaving the window rather than a new negative event.

Impact measures weighted company developments. Attention measures reporting activity relative to its baseline. Company price overlays show Bigdata daily closes in each listing’s currency, on a separate axis from the news signal. The basket price index starts at 100 and compounds equally weighted local-currency returns across available histories. A new listing joins at its first close and contributes returns thereafter. Calendar days without trading carry the prior close; they never borrow a future quote. Source previews are capped at 256 characters, with links to the original reporting.

When enabled, a scheduler advances one completed publication day at a time without rediscovering the basket. Interrupted work resumes from saved progress. Updates include weekends and use verified daily article counts. A day is published only after all four narratives are complete.

Daily and historical attention have different retrieval-window corpora; weights are not guaranteed to be partition-invariant. The website is a published snapshot with an as-of date, not a promise of a continuously running feed.