Dynamic Credit Scoring
Powered by our patented machine learning and artificial intelligence technology, the Trust Science credit scoring algorithms combine traditional and alternative data with consent-based mobile and our proprietary data to deliver in-depth and dynamic credit scoring machine learning models and scores. Trust Science:
- Expands scorable universe and identifies new targets who may not have a complete profile based on traditional methods (e.g. thin-file, no-file, credit invisibles)
- Better matches products and services to targets based on robust credit scoring machine learning models
Trust Science® uses patented algorithms to analyze publicly available digital information. We collect loan data from court data, web searches, transactions and more. Using sophisticated machine learning models and algorithms, we process this data to then determine the creditworthiness of individuals, businesses and organizations.
50+ patents have been officially legally granted to date to Trust Science®
Another 30+ more Patents are Pending around the world
A sample of use cases of this technology includes–but is not limited to–scoring trustworthiness (e.g. for highly predictive, legally-Compliant & socially ethical credit scoring and for loan or insurance portfolio valuation and for marketing & sales-acceleration purposes, etc.)
- You benefit from artificial intelligence and machine learning
- You eliminate human error and automate credit decisioning
- You gain more insights to acquire more and new customers
To date, our patent portfolio covers:
- Mapping the intensity of connectedness between two people (the “six degrees of separation” idea) and among many people/social fabric. "Social Graph"
- The use of an A.I.-infused SIX°SCORE™ in settings from lending to dating to recruiting to law enforcement/counter-terrorism to monitoring one's employees to online commerce or the use of sharing economy sites
- Machine, A.I. and statistical analysis of trustworthiness and connectedness
- The application of trustworthiness in the context of digital currencies (virtual/blockchain)
- The fact that trustworthiness may be context-dependent
- Not only is trustworthiness of a person important, but so is the Risk Tolerance of our users
- Geo-location factors (of both the user and the target) regarding trust assessments
- Identity-matching and Entity-resolution is important for a system like this, which gathers data "in the wild"
- Visually depicting complex, Big Data results
- Determining social connectivity for use in determining trustworthiness
- Permitting entry into, or filtering the ability to view, financial applications based upon connectedness
- Assessing trustworthiness of people, businesses, products, brands, and places
- Improving trustworthiness based on crowd-sourced data
- Trend analysis of direct and indirect data to extrapolate and predict trustworthiness trajectories
We continue to expand our capabilities in the applications of AI, machine learning, big data, and cognitive computing as they relate to context-aware social index scoring and trustworthiness, with additional patents pending.
