Point-in-time market intelligence

Build dossier · Not shipped · Updated July 25, 2026

The product question is not “will this stock go up?” It is: what changed, which entities are exposed, and what evidence was available at the time? This dossier lays out a market-research workspace that joins filings, macro series, and licensed market data while keeping every claim traceable to its source and information timestamp.

Boundary: this is a portfolio build plan, not a live service and not investment advice. The intended output is sourced research support. It does not recommend trades, place orders, or represent a backtest as future performance.

The experience I would build

An analyst opens a dated market pulse and sees the unusual moves first: price, volume, volatility, and cross-asset context. Selecting an issuer reveals newly available SEC disclosures, the macro variables plausibly connected to it, and related companies in an entity/event graph. A generated explanation is useful only when each sentence carries a source link, an observed-at time, an available-at time, and a confidence marker.

The interface would distinguish delayed data from real-time entitlements in plain language. “Current” always means a visible as-of timestamp; stale feeds fail closed instead of silently presenting an old quote as live.

Architecture: evidence before narrative

Point-in-time market intelligence architecture SEC filings, FRED series, and entitled market feeds enter an immutable event log, then a bitemporal store and entity-event graph. Retrieval and deterministic calculations feed a cited analyst brief, with provenance and evaluation alongside the whole path. SOURCE PLANE SEC EDGAR filings + submissions FRED macro series + revisions Licensed feed quotes, trades, aggregates entitlement + delay tagged Immutable event log source identifier event / release time first-seen time content hash append, never rewrite Bitemporal store valid-time truth knowledge-time truth query: AS KNOWN AT t Entity / event graph issuer ↔ security filing ↔ event ↔ theme relation provenance Analyst workspace deterministic metrics retrieved evidence cited synthesis Every card shows: AS OF · SOURCE · DELAY Cross-cutting control plane schema contracts · entitlement checks · lineage · freshness alarms · evaluation traces

Narrative generation sits at the end of the system. The durable artifact is the timestamped evidence graph beneath it.

SEC EDGAR APIs provide filing histories and structured company facts without an API key. The FRED API provides economic series and release data. Prices and trades come only from a feed whose usage rights match the product; for example, Massive documents stock WebSocket feeds. Provider, entitlement, market session, and delay are fields in the data model, not deployment notes.

Entity and event graph

The graph resolves one company across CIK, ticker, security, and legal name, but preserves aliases and validity intervals rather than overwriting history. Events (filings, macro releases, guidance changes, earnings, and abnormal moves) become first-class nodes. Every edge has its extraction method, supporting passage, confidence, and created-at time. A model-suggested relation stays provisional until it is backed by a cited record or a reviewer accepts it.

This makes questions composable: “Which semiconductor issuers mentioned inventory changes after the latest industrial-production release?” is a graph traversal plus retrieval problem, not an invitation for a language model to invent a causal story. The UI separates co-occurrence, reported exposure, and causal evidence.

Evaluation: reproduce what was knowable

Walk-forward evaluation with information-time watermarks Three walk-forward folds train only on information available before each cutoff. Reports, revised macro values, and late-arriving data after a watermark are quarantined from that fold. Evaluation covers retrieval, event detection, attribution, citation support, and calibration. WALK-FORWARD, NOT A RANDOM ROW SPLIT cutoff A cutoff B cutoff C Fold A train evaluate Fold B train evaluate Fold C train evaluate QUARANTINE AFTER EACH CUTOFF future filings · revised macro observations · late vendor corrections · future-derived labels

Each example is reconstructed from the records whose available_at timestamp precedes that fold’s cutoff.

Offline evaluation has five layers: source parsing accuracy, entity resolution, event retrieval, claim-to-citation support, and calibrated uncertainty. Market-facing tasks add walk-forward tests for event detection and ranking stability, but never collapse the result into a promotional “alpha” number. Baselines include simple recency search, deterministic keyword rules, and price/volume z-scores; a model must beat the relevant baseline without degrading citation precision.

GateWhat I would measureFailure response
Freshness Lag from source availability to indexed evidence Show stale state; suppress “now” language
Grounding Reviewer-judged claim support and citation completeness Return evidence cards without synthesis
Time integrity Future-information violations per evaluation fold Block the release; rebuild the snapshot
Uncertainty Calibration by event type, sector, and data regime Abstain or label the relation provisional

Build sequence and definition of done

  1. Evidence spine: ingest EDGAR and a small FRED allowlist into versioned snapshots; ship search with citations before adding generated prose.
  2. Point-in-time graph: resolve issuers and events, record both valid time and knowledge time, and replay any historical query exactly.
  3. Market context: add an entitled price feed, label its latency, and join deterministic move detection to sourced events.
  4. Synthesis: generate only from retrieved evidence, verify citations, expose uncertainty, and log the full trace for review.

I would call the first release complete when a reviewer can select any sentence in a brief, inspect the exact source version and timestamps, rerun the query against the same information set, and see the system abstain when evidence is insufficient.

Primary documentation

  1. U.S. Securities and Exchange Commission, EDGAR application programming interfaces.
  2. Federal Reserve Bank of St. Louis, FRED API documentation.
  3. Massive, stocks WebSocket overview (an example vendor interface; access rights must be verified for the deployment).