Google News Competitive Event Intelligence

Use this Actor to analyze google news competitive event and return decision-ready structured signals. It is designed for repeatable human, API, Apify AI, and MCP-driven workflows.

Convert Google News exports into company-event relevance, narrative velocity, competitor impact and alert-ready intelligence. This Actor is designed as a decision layer over current and historical datasets, so teams can reuse extraction they already trust instead of paying twice for the same collection work.

Why use this Actor

Raw marketplace exports are useful, but they usually stop at rows and fields. Google News Competitive Event Intelligence adds deterministic scoring, explicit change detection, and action-ready output. It accepts inline records or an Apify Dataset, compares a previous snapshot when supplied, and returns a consistent decision surface for dashboards, workflows, agents, and recurring monitoring.

The design deliberately separates extraction from intelligence. That makes the Actor easier to maintain when a source website changes and lets users combine it with any compatible upstream scraper. Scores are transparent and based on documented fields rather than an opaque mandatory LLM call.

Key features

• Dataset-first workflow that works with upstream Apify Actors or your own normalized exports.
• Deterministic signalScore, changeScore, agentAction, and agentReason on every result.
• Current-versus-previous snapshot comparison for recurring intelligence.
• Low-memory 256 MB runtime and predictable pay-per-result economics.
• Structured Dataset output plus an INTELLIGENCE_REPORT key-value summary.
• Useful defaults for one-click testing before wiring a production Dataset.

Input

Provide currentItems for inline analysis or currentDatasetId for an upstream Apify Dataset. For change intelligence, also provide previousItems or previousDatasetId. maxItems limits how many records are analyzed in one run. The Actor does not require credentials for the source platform because the stable workflow starts from supplied or upstream-collected data.

Output

Each row contains the original source record plus signalScore, changeScore, agentAction, agentReason, normalized metrics, detected field changes, and an observation timestamp. This makes the Dataset suitable for filtering, automation, alerts, portfolio review, and AI-agent tool chains.

Example

A recurring workflow can run an upstream scraper daily, pass its Dataset ID as currentDatasetId, pass yesterday's Dataset as previousDatasetId, and use only records whose agentAction indicates a material opportunity or risk. This avoids rebuilding the same comparison logic in every automation.

Use cases

Use it for competitive monitoring, market research, prioritization, change alerts, analyst triage, recurring portfolio reviews, and agent workflows where raw records need a consistent action layer. It is especially useful when the source has many rows but human attention should be spent only on the highest-signal changes.

Pricing

The primary event price is $0.0035 USD per decision-ready result row. There is no separate analytical start fee in the product design. Users can control spend with maxItems and by filtering upstream data before analysis.

Limitations

This Actor analyzes the records supplied to it; source completeness depends on the upstream scraper or dataset. Scores are decision support, not predictions of financial outcomes. Field conventions can differ between upstream Actors, so the sample schema should be normalized when necessary. Only public or appropriately licensed data should be processed. Snapshot intelligence is meaningful only when entity identifiers are stable across periods.

Workflow design

For production use, keep extraction and intelligence as separate steps. This makes source replacement easier, allows historical snapshots to be retained independently, and lets the same intelligence Actor consume data from different collectors. The output schema stays stable even when the upstream extractor changes.