Executive summary

Strise’s Adverse Media Screening (AMS) detects adverse media events using natural language processing (NLP), knowledge graph insights, and keyword searches. It analyzes news data and provides structured insights for Companies and Persons.

Automation and Monitoring capabilities

Strise leverages advanced automation to streamline the monitoring of adverse media events. By processing raw data in real-time, Strise can dynamically monitor AMS events across your portfolio of companies and persons. This capability enables users to receive timely and actionable insights, ensuring that adverse media risks are identified as soon as they arise. With automation at the core, Strise reduces manual effort and enhances the efficiency and precision of adverse media detection.

How it works

1. Data collection

Strise’s AMS begins with analyzing a vast number of news articles and reports. Each day, we process approximately 3 million articles from more than 70 countries, ensuring global coverage and real-time updates.

Primary data source: Articles are sourced primarily from Opoint, a leading provider of media monitoring.
Supplementary data: In specific markets, Dow Jones Watchlist Feed is used as a supplemental data source.

<aside> 💡

</aside>

2. Data Normalization and Structuring

Collected data is normalized and structured by running it through Strise’s NLP pipeline. This process involves:

Translation and standardization: Content is translated (if needed) and converted into a common format.
Event identification: The pipeline detects specific events relevant to adverse media screening topics defined in our Knowledge Graph hierarchy.

<aside> 💡

</aside>

3. Knowledge Graph Integration

The Knowledge Graph plays a critical role in identifying and structuring adverse media events:

AMS topics: Events are linked to topics within the Knowledge Graph. Examples include corruption, financial crime, trafficking, and war crimes.
Entity matching: Adverse media events are connected to relevant entities (persons or companies) to ensure precise identification and linkage.

<aside> 💡