From opening a bank account to applying for a mortgage, millions of people submit applications to thousands of banks around the world every day. Processing these applications and ensuring that the people applying are legitimate customers is a daunting challenge – a challenge that is compounded by the rapid digitalization of bank services. Mobile banking has all but replaced in-branch visits, and applying for a loan now only takes a few clicks. In this era of unprecedented digital access, banks must rapidly innovate to meet the current and future demands of their customers. As such, banks have prioritized rolling out slick online experiences that outshine their competitors.

Payment provider PayPal continues apace with its acquisitions streak to bring more modern tools into its platform to serve its 237 million customers. Today the company announced that it is buying Simility, a fraud prevention specialist, for $120 million in cash. PayPal had been an investor in Simility (it owns three percent of the company, it says), along with Accel, the Valley Fund, Trinity Ventures and others. The startup had raised just under $25 million and was last valued at $52.75 million, according to figures from PitchBook, making this a decent return for its backers. The deal is expected to close in Q3.

PayPal has acquired its second startup in as many days, as the payments giant announced today that it was snapping up machine learning-powered fraud detection startup Simility. The transaction is valued at $120 million, in what will be an all-cash deal. The news comes two days after PayPal bought out payments startup Hyperwallet in a $400 million deal. Founded in 2014, Palo Alto-based Simility leverages machine learning to help those working in the fraud detection sphere collect and analyze data. The platform is designed to prevent myriad kinds of fraud, such as account takeover (ATO), where a bad actor tries to gain access to another person's online account. In such a scenario, Simility looks at various session, device, and behavioral biometrics and builds a profile for what constitutes "normal" user login behavior; if an anomaly is spotted, it can act to prevent the action.

Payment provider PayPal continues apace with its acquisitions streak to bring more modern tools into its platform to serve its 237 million customers. Today the company announced that it is buying Simility, a fraud prevention specialist, for $120 million in cash. PayPal had been an investor in Simility (it owns three percent of the company, it says), along with Accel, Trinity Ventures and others. The startup had raised just under $25 million and was last valued at $52.75 million, according to figures from PitchBook, making this a decent return for its backers. The deal is expected to close in Q3.

Join Julie Conroy, Aite Group, and Swastik Bihani, Simility, to learn how companies are using machine-learning models and behavioral analytics across a wide variety of structured and unstructured data to accurately detect fraud and suspicious activity. You'll see how you can easily clean, transform, enrich, and deep dive into all the related suspicious activity that makes a potential transaction suspect. We'll cover how these techniques yield insights from professionals in threat detection, fraud, security, and compliance use cases. Whether in a private cloud or on premise, you'll see how your analytics stack can become clean, flexible, and accessible through an easy-to-use UI--no coding required.

One area of machine learning that's getting a lot of buzz in recent years is artificial neural networks (ANNs), aka "deep learning" models, which try to simulate how layers of neurons act together in the brain to make a decision. ANN models are highly versatile and can be used to solve highly complex problems like identifying account takeover using the device's sensor data. While other techniques often require limiting the number of features, multi-layer ANNs can train on thousands of features and scale easily. You may be thinking, "Why not just use deep-learning models all the time?" Training such models requires massive amounts of data (typically, millions of labeled transactions), so deep learning models are really only practical for large companies or those that generate a lot of data points.