Features
Core Features
Urvin.Discover makes sense of unstructured data. It does not require training and is built for high-performance, high-scale applications. It has very broad knowledgebase and can be extended for your company’s unique set of language and acronyms.
Extremely High Performance
Our unique technology can index and search through documents far faster than other approaches.
Domain-Specific Knowledge
Our NLP solution can be extended into custom language datasets such as finance, legal and automotive.
Entity Recognition + Linking
Proprietary approach to entity recognition and linking, and we leverage open source approaches as well.
Multi-Language Support
Multiple languages out-of-the-box, and we do not require extensive training to support additional languages.
Phrase Detection + Counting
Unique ability to find and count key phrases at-scale is superior, especially relative to cloud-based NLP systems.
Quantitative Awareness
Can identify currencies, dates and numbers in-context leading to deeper insight into meaning and patterns.
Modular Architecture
No one-size-fits-all approach. Features are modular and can be integrated in custom ways to solve unique problems.
Transparent Explainable AI
No mysterious black box. All insights, classifications and matches can be explained, with complete transparency.
Use Cases
Use Cases
Urvin has taken on the most difficult use cases, and helped firms transform how they approach these challenges. Our approach is able to deliver unique insight and dramatically increase efficiency.
Research + Discovery
Urvin.Discover can index document repositories, along with unstructured data across multiple data sources. Our unique concept-based search system searches and locates relevant resources, assembles insight to support your analysis and finds information that counters your argument.
Financial Services
Index and search financial services documents that make heavy use of industry-specific terms and jargon. Examples include EDGAR filings, SRO filings, and investment banking pitch documents. Urvin.Discover has proven its ability to understand these topics at the same level as an expert in the field.
Legal, Merger + Acquisitions
Quickly search through large numbers of contracts looking for key phrases or clauses. One example was to find all “Assignment” clauses for an M&A transaction and confirm that they were appropriately worded, flagging those that weren’t for further review.
Tax Classification
Quickly classify products for tax purposes according to their natural language descriptions. Urvin has done this at-scale in a fully transparent and explainable way.
Aerospace + Defense
Document discovery across large stores in multiple languages to quickly identify relevant documents, and help knowledge workers avoid redundant work.
Pharmaceutical
Take your early phase trial data and make predictions on the likelihood of success of subsequent phases. Use Urvin’s prediction capabilities to help identify how new medications will be effective, and to develop inclusion/exclusion criteria for drug trials.
Data Leader at Knowledge Management CompanyWhat I’ve seen is impressive. This is the first actual demonstration of viability that I have seen from any company that can take our data and work at our scale. This is remarkable speed and remarkable quality.
Thoughts
AI Thoughts + Insights
Case Study
Product Classification for a Global Tax Software Company
Helping one of the largest e-commerce platforms in the world figure out if there was an automated, scalable way to classify the product to collect the appropriate sales tax.
Case Study
Data Linking for a Noisy, Huge Dataset
Urvin was approached by a firm who needed to process petabytes of noisy data with a reasonable hardware footprint and processing time.
Case Study
Pharmaceutical Prediction for FDA Phase 3 Trial
A pharmaceutical company about to begin an FDA Phase 3 trial needed to find a partner who could make predictions on a small, very noisy dataset with confidence.