The ability to glean real-time insights about customers, markets, and internal operations is critical today. Opportunities and risks abound and the ability to spot them faster can be the difference between success and failure.

Person-to-person payment (P2P) is a rapidly growing payment system within Capital One and all the other big banks in the U.S. Performing fraud analysis for each payment request is critical. This talk covers Capital One’s move from a micro-services-based fraud detection system to a new system that relies on stream processing (Apache Flink) and machine-learning to detect fraud.

To support a modern data architecture and approach to analytics, data integration strategies now support on-prem, cloud and hybrid deployments. Meanwhile, streaming architectures featuring change data capture (CDC) technology are rapidly being embraced to process data in motion. This session will discuss the new requirements and best practices to be successful in enabling a real-time enterprise, whether in a data lake, via streaming technology, or in the cloud.

Today, data is increasingly seen as the fuel of the business, rather than its byproduct. As a result, there is greater need to ensure data is of high quality.

The old adage “garbage in, garbage out” couldn’t ring truer when it comes to maximizing the value of machine learning in the enterprise. Machine learning is worthless if it’s fueled by bad data. This discussion helps attendees thread through the noise and understand exactly how to get the most out of machine learning by making their dirty data come clean. Learn more about the difference between machine learning, artificial intelligence, and deep learning; why collecting massive amounts of data simply isn’t enough to glean value from machine learning technology; what’s real and what’s hype when it comes to machine learning; and how to use machine learning to predict, identify patterns, and optimize processes.

Big Data is challenging the status quo and spurring disruptive new technologies and services. Understanding the tools and technologies that are available, and the pros and cons of each is critical to making the right choices.

As Big Data grows, there is the opportunity to explore and manage larger data volumes for business value. But with seemingly endless commercial, open source, and “as-a-service” offerings hitting the market each week, how do you choose the right mix of technologies and avoid creating an accidental architecture that will limit you from future innovation? How are organizations actually achieving true bottom-line benefits from their Big Data initiatives? This talk helps you understand how your organization can adopt an effective and agile approach to Big Data analytics while focusing on the analytical use cases that deliver a bottom-line and competitive impact.

Big Data has significant implications for industry and government. But it is not enough to collect large quantities of data and securely store it. Succeeding with Big Data in the real world requires planning and preparation.

In video games, players learn by failing—even if they have to “die” hundreds of times before learning how to succeed. By enabling us to simulate scenarios and predict outcomes, AI and Big Data have essentially made the world similar to a game that we can play with, yet we still expect immediate success. Is this realistic? In this presentation, technologist Weller explores the role of failure in machine learning using real-world examples.