Fortune 50 Bank Develops Custom News Analytics in Days
A Fortune 50 bank uses Snorkel Flow to identify various companies’ mentions by role and sentiment in unstructured news feeds.
Deeply Understand the Impact of News
Snorkel Flow lets you build custom applications that analyze news and extract entities, events and relationships precisely. Go beyond brittle, off-the-shelf data feeds today–no costly manual labeling required.
With rising demand for affluent stay-at-home consumers, interactive fitness bike maker Peloton [ENTITY] agreed to buy [EVENT] Precor [ENTITY], a major provider of workout machines to gyms and hotels, for $420M [PRICE], its biggest purchase to date.
Faster, Lower-cost Extraction
Is Peloton mentioned in this news article?
Is Peloton’s mention focal or auxiliary?
Is the news article about M&A?
A Radically New Approach to AI
With Snorkel Flow
With Conventional Approaches
How Snorkel Flow Works —
An End-to-end ML Platform Centered Around Data
Designed to accelerate AI application development by removing the training data bottleneck.
AI Use Cases
Build and deploy use cases previously blocked by training data by combining state-of-the-art ML with industry-specific best practices and flexible API-based integrations using Snorkel Flow.
Classify policy documents on the basis of the behavior or occupation to assess risk.
Build customized promotions by analyzing customer behavior and demographics.
Determine clinical trial candidates by categorizing patient records.
Extract entities, events, and relationships to improve investment and risk strategies and more.
TELECOM & CYBER
Understand every customer interaction deeply by analyzing chats, emails, and tickets.
Manage credit risk by collecting financial and non-financial data in any format from statements.
Identify named entities in customer search queries and optimize content on websites.
Enhance recommender systems by identifying entities (price, keywords, etc.) in product descriptions.
Extract and organize data from a wide variety of complex contracts efficiently.