AWS Startups Blog

Category: Amazon Machine Learning

Machine learning on limit order book data for surveillance and compliance

There are two key types of market participants; those who are trying to make money from the markets and those who are assigned to police those trying to make money. Examples of the former type include investment banks, hedge funds and asset managers, while examples of the latter includes in-house compliance, financial regulators and exchange surveillance teams.

Read More
Density CEO Andrew Farah

What if you could AB test the physical world? Density makes it possible

These days, distributed teams have plenty of enterprise software options that make collaborating feel seamless. But actual, face-to-face, IRL workplaces have been somewhat left behind. That’s where Density comes in. The San Francisco-based startup has built a piece of enterprise hardware for corporate campuses that measures how space is used. Many believe the technology is key to optimizing how all physical space is used.

Read More
A screenshot of the Visipedia Bird app.

Caltech’s Pietro Perona on how deep learning can help you classify birds and trees

Imagine, for a moment, that you discover an irregular mole on yourself. Whereas nowadays you still need to take time to schedule a dermatological appointment and then wait weeks to get your test results, Caltech Professor Pietro Perona is eagerly awaiting the day when you can snap a picture of the mole with your smartphone and then learn instantaneously if it’s dangerous or not. And he should know. As the co-creator, with Cornell Tech Professor Serge Belongie, of the AI and machine learning-based visual classification system Visipedia, Perona has spent the past seven years working on a “switchboard” that lets anyone, everywhere ask questions and immediately obtain an answer.

Read More
João Menano on Expanding Credit Opportunities with AI

James CEO João Menano on expanding credit opportunities with AI

Assigning credit risk to people who apply for business loans, credit cards, and home mortgages has mostly been done by weighing some 10 or 20 attributes. Take those attributes—and we’re all familiar with some of the things that make our credit scores rise and fall, including timeliness of payments, debt to income ratio, and defaults—and crank them through your favorite logistic regression model or scorecard. The result is your assigned credit risk, and depending on the number, you either get your loan or you don’t.

Read More