GlassesUSA.com is the fastest-growing, leading online eyewear retailer serving a mass market with a broad variety of products. As a disruptor in the eyewear category, GlassesUSA.com continues to innovate the industry with tools that further the brand's mission, including its proprietary Prescription Scanner App and the Virtual Mirror. Over the years, they’ve made innovation and growth a priority but were lacking a tool to advance their user experience through machine learning. Explorium was the missing link — unlocking data science and building accurate machine learning models that were translated into personalized experiences for their web and mobile users.
No other platform does it all: automatically join your data with a broad range of datasets, extract and sel...
Like that? You might also like...
The current credit scoring model is outdated and in need of an upgrade. Read how to go about building a smarter, more accurate credit scoring model - and the data you need to do so.
In this article, we explain why you should use external data for effective Know Your Customer (KYC) programs. The post To Really Know Your Customer, You...
In this blog post, we look at the shortcomings of conventional credit scores and ratings and explain how to improve your models.
In our interconnected, globalized world, it’s harder and harder to track the weak spots in your supply chain. That’s why we created this handy guide to understanding and mitigating supply chain risk.
In this in-depth guide, we reveal the real reasons your machine learning risk models are falling short, what you can do to fix them — and exactly how to tackle the problem.
Risk and probability are based on data. You establish the statistical risk of losing an investment based on other investments that didn’t work out. You assess The post What Happens When The...
In some ways, OZARK’s main plot seems too good to be true, and it might actually be. In the real world where ML-powered risk models exist, could Marty Byrde really get away with his schemes?
Dynamic risk models add a dimension to rules-based risk modeling that makes you more agile to the changing world.
Your organization’s risk management strategies are going to need a major overhaul. Insights from your historical data simply won’t be enough to help you assess the risks that are coming your way.
CROs need to upgrade their visibility, which requires looking outside their organizations for data. But, how can they be effective when collecting external data can take weeks or even months?
Walter White and Marty Byrde are known for their money laundering schemes. But could they really fool the best risk models banks have today? Let's look.
During crises, risk takes on a whole new meaning, and assessing it becomes more important, but also much more complex.
With ML models rendered useless, we built an entirely new set of COVID-19 signals in our platform that let organizations understand their risk derived from the current pandemic.
For lenders, pre-COVID-19 data is no longer useful in a post-COVID-19 world. Here's how we're giving our customers external data to ensure their risk models work in our new reality.
It’s time to look outside of our own silos to external data and make sure that despite the crises we face, we can give our organizations the power to make it through. The post Tomorrow Comes Today –
Explorium is the future of data science. We enable you to automatically connect to thousands of data sources, distill the best features, and deploy the best models.
There are some insights that can only come from the data you produce or collect in-house. Historical sales figures, for example. Foot traffic through your store. The post How SMBs Can Boost Their...
Building core operations around ML models has helped many companies thrive across many other verticals. Still, others wait to implement at a large scale. Why?
You don’t know what you don’t know, as the old saying goes. But in the age of Big Data, you simply can’t afford to shrug off "unknown unknowns".
No other platform does it all: automatically join your data with a broad range of datasets, extract and select the best set of features, and build production-ready models.