How Rodz Produces Intent Signals: 350 Scrapers, 250+ Sources

The Collection Infrastructure

350+ scrapers running continuously

An intent signal does not appear out of thin air. Behind every detected event, there is a massive collection infrastructure. Rodz operates more than 350 scrapers that continuously query public and partner data sources. This infrastructure relies on specialized platforms like Apify to orchestrate and run crawlers at scale. Each scraper is specialized for a particular source type (business registry, job board, professional social network, sector-specific database) and optimized to extract relevant information without overloading source servers.

These scrapers run 24 hours a day, 7 days a week. Query frequency varies by source: some registries are updated daily, others in real time. The goal is to detect every event within hours of its publication.

250+ cross-referenced data sources

The 250+ sources queried cover the full digital footprint of businesses:

Legal and administrative sources

SIRENE: registrations, address changes, statutory modifications
Commercial registries: financial filings, capital increases
BODACC: legal notices, transfers, liquidations
Legal announcement journals: official publications

Employment and HR sources

General job boards (Indeed, HelloWork) and specialized ones (Welcome to the Jungle, Talent.io)
LinkedIn: job postings, executive role changes
Company career pages

Financial sources

Press releases: funding rounds, partnerships, financial results
Investor databases: funding rounds, valuations
Industry publications

Media and social sources

LinkedIn: posts, comments, engagement signals
Industry press: articles mentioning target companies
Google Maps: new locations, address changes

Cross-referencing sources

The value of Rodz does not lie in any single source taken individually (anyone can check SIRENE or Indeed, or spin up a scraper on Apify). It lies in cross-referencing these sources. Massive hiring detected on Indeed, cross-referenced with a funding round identified in a press release, cross-referenced with a leadership change on LinkedIn, forms a composite signal far more powerful than any single event in isolation.

The 108 Signal Types

A comprehensive taxonomy of commercial events

Rodz categorizes events into 108 signal types organized into major families:

Growth signals: hiring, capital increases, office openings, headcount growth
Transformation signals: executive appointments, mergers/acquisitions, reorganizations, strategy changes
Intent signals: solution research, event attendance, tech stack changes
Regulatory signals: compliance initiatives, certifications, patent filings
Financial signals: funding rounds, published results, investments

Each signal type has its own characteristics: detection frequency, strength of the revealed need, relevance window, and sector-specific applicability.

222 configurations per signal

The same signal type is not interpreted the same way depending on context. Hiring 3 people does not carry the same meaning as hiring 30. This is why each signal can be configured using 222 parameters:

Trigger thresholds: minimum number of hires, minimum funding amount
Sector filters: industry codes, keywords in business description
Geographic filters: departments, regions, countries
Size filters: minimum/maximum headcount, revenue
Role criteria: type of position being hired, seniority level of the new executive
Combinations: associating multiple signals to create composite signals

This granularity allows each company to configure detection that matches their specific offering and market.

The Verification Process

From raw signal to actionable signal

A raw event is not an actionable signal. Between detection and delivery to the sales rep, several processing steps take place:

Deduplication: the same event may appear across multiple sources. Rodz eliminates duplicates to deliver only one signal per event.
Contextualization: the signal is enriched with company information (size, sector, history) so the sales rep can understand the context at a glance.
Balance Scoring: the proprietary model assigns a score combining the nature of the signal (strength of the revealed intent) and its recency (a coefficient that decays after 48 hours).
Deep Search Enrichment: the right contact’s details are identified via a SIRENE > Google Maps > LinkedIn cascade, with 80 to 85% accuracy on professional emails.
Delivery: the enriched, scored, and contextualized signal is delivered to the client’s CRM or via the Rodz interface.

The 48-hour rule

This entire process (detection, verification, enrichment, scoring, delivery) must complete within 48 hours of the event. This deadline is not arbitrary: Rodz data shows that a signal loses 80% of its value beyond this threshold. The prospect has already been contacted by competitors, has started their own research, or has been absorbed by other priorities.

The Numbers That Matter

The Rodz infrastructure produces measurable results:

4 actionable signals per company per year on average
4x qualified meetings compared to cold prospecting
+74% closing rate thanks to timing relevance
15 hours saved per week per sales rep

And a single KPI to measure effectiveness: the positive response rate. Never open rates or click rates, metrics skewed by tracking pixels and security filters.

Want to leverage this infrastructure yourself? Check out our getting started guide with the Rodz API for authentication and your first request, then the complete API reference to explore all available endpoints.

Frequently Asked Questions

How long does it take to configure the signals?

The Creation phase (initial configuration) takes 1 to 2 weeks. It includes an audit of your offering, selection of the relevant signals from the 108 available, and setup of the 222 configurations. The first signals are delivered as soon as this phase is complete.

Yes. Rodz only collects data from public sources (registries, press releases, job postings, professional profiles). Deep Search enrichment uses exclusively professional contact details. The right to object is systematically offered in every outreach.

What happens if a signal is false or outdated?

Multi-source cross-referencing mechanisms significantly reduce false positives. A signal detected on a single source is verified against others before delivery. The Balance model’s recency coefficient automatically downgrades signals that age past the threshold.