Rumor Hound autonomously monitors a continually increasing universe of news and social chatter for M&A rumors. Rumor Hound rewards low popularity sources that publish rumors that are cited by higher reliability sources at a later date and penalizes higher popularity sources that are late to report. Over time, Rumor Hound surfaces superstar sources with low reach and influence that for one reason or another are highly accurate in publishing market moving M&A rumors.
Automate the discovery of new sources of M&A chatter to deepen your analysis and surface valuable insights.
Organize millions of disparate data sources into one dashboard and identify credible M&A chatter before Wall Street.
Know which sources are most reliable at publishing rumors that move stocks and keep pace with significant developments.
Trade rumors early in the information cycle. Identify superstar sources and stocks likely to outperform the S&P 500.
Understand the reasoning, source quality and market-moving potential of every new piece of data.
Surface M&A chatter early on. Identify emerging trends and unique insights unlikely to be priced in.
Autonomously grows the number of relevant sources that publish information related to mergers and acquisitions.
Instead of traditional web crawling and scraping, Rumor Hound employs proprietary data listening processes that extract data hidden to the UI allowing the user access to more feature rich data.
Understand how reliable a source is in publishing information that successfully impacts the market regardless of popularity.
Differentiate the popularity of a source without bias. The algorithm dynamically adjusts to refine and increase the accuracy of the scoring.
Surface higher-value insights. The machine dynamically adapts to incorporate new information and shifts in context - developing a richer understanding.
Filter by standard and custom Accrete metrics like estimated price impact, popularity, and reliability to surface insights that suit your trading style.
Accrete’s Topic Classification Knowledge Function can understand the semantic and contextual nature of an individual sentence within its surrounding environment and specific to the domain of the text itself using language understanding. Topic Classification can provide a deeper level of understanding as meticulously as a human at scale.