Cloud Hosting

Businesses, health systems, utilities and even governments run on data unseen torrents of it constantly sloshing back and forth across globe-spanning networks, at a speed and volume too large for any human brain to fathom. Fraudsters often lurk within that hidden world, exploiting weaknesses in systems or using crafty techniques to mask their activities.

Organizations can use big data technology to guard against various types of fraud, from data breaches to false claims that an item never arrived, by training algorithms to recognize what is and is not normal behavior within a system. The technology required for such operations is complex and requires big investments from e-commerce experience builders like Signifyd, which uses data science technology to protect its customers from abuse. Meanwhile, cybersecurity outfits like ActZero use similar technology to help businesses recognize the potential presence of hackers within their own systems.

To learn more about what data science-driven cybersecurity looks like in practice, we caught up with data science leaders at Signifyd and ActZero.

Diana Rodriguez

Senior Director of Data Science

Company background: Signifyd helps retailers produce e-commerce experiences for customers. The company provides a financial guarantee against approved orders that turn out to be fraudulent, which places data security for customers and vendors front and center.

Describe the data sets your technology runs on and how that data is collected.

Our data sets consist of hundreds of billions of dollars worth of transaction data from thousands of online merchants selling in every retail vertical in more than 100 countries around the world. If you want to envision that data set of transactions, think of a top 10 online merchant. Now think bigger and bigger still. That commerce network is at the core of what we do, and I constantly work with and on the technology that drives it. Our data is enriched with data sets from third-party providers, which amplifies our ability to understand the identity and intent of every order placed on our global commerce network. Our commerce network data is collected through API custom integrations with some retailers and through standard Signifyd applications available through all the major e-commerce platforms such as Shopify Plus, Magento, Salesforce, BigCommerce and others.

Signifyds models harvest their most valuable insights from behavior patterns that indicate whether an e-commerce order is legitimate or fraudulent, or whether a customer complaint involves an honest failure on a retailers part or a dishonest attempt by a fraudster to take advantage of the retailer. Those anomalies can come in the form of disparities between shipping addresses and billing addresses, transaction history, device ID and location, among thousands of other signals.

What are the most valuable insights or patterns you look for in the data?

Our challenge is to apply the latest developments in machine learning to turn fuzzy concepts like trust into solvable, quantitative problems. Do I trust this order and the consumer behind it? Secondly, fraud is an adversarial problem. Unlike, say, a self-driving car, where the innovators, developers and society at large all share an interest in making sure the artificial intelligence involved works well and evolves into better versions rapidly, fraudsters are out to foil our artificial intelligence. As we become better and our solutions become more effective, fraudsters shift their targets and tactics. We need to anticipate these moves and stay ahead of the competition. It certainly makes life interesting.

By analyzing transactions on multiple data points, we are able to see the full picture and better distinguish the good from the bad, as well as enable merchants to properly enforce policies that meet their business goals. Watching the changes in behavior through the data has inspired Signifyd to develop additional solutions for merchants, including those tackling unauthorized reselling, fraudulent returns and false claims that an ordered item never arrived, to name a few. All the while, as we analyze patterns, adjust the model and evolve our view of fraud, we need to keep in mind that the primary goal is not stopping fraudsters but enabling good buyers to buy. That makes life better for end consumers and also for our merchant-customers, who see higher revenue and build customer lifetime value for their enterprises.

It can be dangerous to rely too heavily on one data point.

What are some of the potential drawbacks of using data science to solve problems like fraud, and how can technologists avoid or mitigate them?

We can never forget that the machine learning models we build to make data understandable and actionable are the products of human minds. Human minds are wonderful things, but they come with biases, preconceived notions of outcomes and they are not flawless. Because humans conceive of and develop models, they also can inject human biases into the model, which by extension introduce biases into the outcomes the models produce.

Data scientists apply various model interpretability methods to balance high model performance and accountability and explainability. Data scientists are building very complex models. Employing interpretability methods is one way to better explain how our models function and diagnose issues of bias or fairness that might otherwise go undetected.

One advantage to drawing on a vast number of signals to achieve our decisioning is that the anomalous patterns that we look for are based on thousands of signals,and therefore, we do not ascribe too much weight to one or two signals. It can be dangerous to rely too heavily on one data point. For example, consider the case of account takeover fraud a misfortune in which through obtaining passwords, for instance, a fraudster takes control of a legitimate consumers account. If decisions were based solely on the behavior of that email address, the account would appear suspicious and the legitimate consumers ability to transact would be compromised. Thats why our models base their decisions on a multitude of signals.

How do you think data science technology will evolve over the next year?

Like all science, data science will continue to advance through experimentation, trial and error, vigorous debate and rigorous study. Most of all, it will continue to advance through collaboration. Data science is moving fast and its power is being extended to more and more facets of our everyday lives. New ideas and techniques are being shared every day. Understanding how we can build off of the collaboration in the space to continue to refine and explore new ways of building models will be an ongoing pursuit. Flexibility in experimentation will be key, with clear goals guiding the continuing exploration.

Alexis Yelton

Director of Data Science

Company background: ActZero provides an AI-powered security platform for small and medium-sized businesses, detecting anomalies that may betray the presence of bad actors within a system. The company raised $40 million in funding earlier this year, which it is using to publicly launch its product.

Describe the data sets your technology runs on and how that data is collected.

We build ML and mathematical models on computer, network and cloud software logs in order to detect and respond to cyber threats. This data is semistructured and very big we see terabytes of data per day.

What are the most valuable insights or patterns you look for in the data?

We look for two kinds of patterns in the data. The first is patterns known to be indicative of cyberattacks, including but not limited to known suspicious commands, suspicious processes executing and command line character entropy. The second is patterns that indicate anomalous behavior. For these, we learn what is normal behavior for a user, machine or customer and highlight unusual behavior using anomaly detection algorithms.

We build simple features that can serve as output in their own right, then more complex ones.

What are some of the potential drawbacks of using data science to solve problems, and how can technologists avoid or mitigate them?

The biggest drawback is obvious but essential to understand: Machine learning models and even simpler mathematical models are costly to build, run and maintain. You need a robust code framework and infrastructure to process data and to run and monitor algorithms. These types of models also require substantial maintenance.

We have spent a great deal of time mitigating these issues at ActZero, and we do so in a number of ways. Firstly, we take an iterative but also additive approach to rolling out models. We build simple features that can serve as output in their own right, then more complex ones. All of these are input into a feature store from which future pipelines can draw. Then we build heuristics based on logic and statistics that use these features to produce meaningful predictions. Finally, we build an ML model if there is a business case for one. We reuse our framework mainly via our feature store and data science pipelines as much as possible to accelerate and simplify productionization.

How do you think data science technology will evolve over the next year?

There has been a proliferation of companies that sell machine learning frameworks for feature stores, ML pipelines and auto-ML. Over the next year, I see these dropping in cost and experiencing significant market adoption as the need grows for data science solutions.

Here is the original post:

Data Science Is a Key Weapon in the Fight Against Fraud - Built In

Read More..

The Center for Naval Analyses (CNA), a Federally Funded Research and Development Center (FFRDC), is sponsored by the Department of the Navy and headquartered in Arlington, Virginia. CNAs mission is to help Navy and Marine Corps leaders ensure Americas defense in the 21st century. CNA is unique because of its real-world, empirical, and data-driven approach to operations analyses and use of data scientists as expert observers of military operations. CNA is the nations oldest operations research organization with lineage tracing back to World War II (1942) when CNA scientists went to sea aboard Navy ships to observe and analyze anti-submarine warfare operations in order to help defeat German U-boats. Its research staff has diverse educational disciplines with nearly 70% with Ph.D. degrees and 92% having graduate-level degrees.

Tim Kao is the Vice President of Data Science, CAN. He has served in the United States Marine Corps for 20 years, including being a part of two combat tours to Iraq and Afghanistan. During those two decades, Tim served in the artillery, special operations, space, jungle warfare, and operations analysis commands. He received a B.S from the Air Force Academy, an MBA from the University of Colorado, and a Masters in Operations Research from the Naval Postgraduate School. Tim started working at CNA in 2015 and is currently the Vice President of Data Science. As the VP, he has the privilege of leading over 25 data scientists that are collaborative partners with Navy and Marine Corps sponsors and committed to supporting Americas naval services.

Data scientists rightfully focus on relationships between features and variables. However, leadership, even for data scientists, is fundamentally is about relationships with people. As a young jumpmaster instructing parachuting at the Air Force Academy, Tim quickly learned that the safety and success of personnel learning to jump out of airplanes depended on the trust and relationship they had with him as their instructor. If that was lacking, the probability of having students that refused to jump increased significantly. In the Marines, Tim worked for some great leaders and some extremely bad ones. The difference between those two types of leaders came down to the relationships those leaders were able to establish with those people they led. Leading data scientists is no different. Tim values a data scientists technical skills, but their ability to exhibit the extremely hard to master soft skills is just as important. That is how CNA try to hire (and are hiring!) and it contributes to the teams success.

Tim presumes that the ever-evolving discipline of data science requires a constant refresh on emerging algorithms, technologies, and processes. He says that when he joined CNA, he was coming from a USMC assignment as the commander of the only jungle warfare training center in the Department of Defense as well as a recent deployment to Afghanistan. While Tim was able to use some of his data science knowledge to support those military units, many of my data science skills quickly atrophied, as he did not use them regularly. According to him, overcoming this challenge required a growth mindset to catch up quickly on emerging machine-learning techniques and code. This continues to be a challenge today as new things in data science are released every day. A growth mindset is critical for a data scientist for continued success, highlights Tim.

Tim opines that data science leaders have to be curious and caring. He adds that being curious is important because leaders wont know everything but need to know enough to search out an answer through research and collaboration with others. Being caring is also vital because Tim remarks that he really believes in the truism that no one cares how much you know until they know how much you care. Leading data scientists really isnt much different than leading people in combat. You have to know yourself (what are your data science capabilities), know your enemy (what is the problem being solved), and take care of your troops (data scientists) so they want to do a good job for each other and you, asserts Tim.

Tim explains that CNA uses concepts like developing minimum viable products (MVPs) to iterate with its Navy and Marine Corps sponsors. They are an integral part of the process in the creation of a data science solution CNA is developing. CNA not only works with them on the user interface, but collaborates with them to understand the data, how it is collected, what is missing, and assumptions the company needs to make. A successful data science effort requires both superb data scientists and a tight partnership with the end-users the analytics.

Tim exclaims that leaders have to ensure their data scientists have opportunities to leverage disruptive technologies in their work. Like other professions and even more so, data scientists want to do innovative and meaningful work. Its incumbent on data science leaders to provide that opportunity. He adds that even if data science team members think they are too busy doing work to learn new things, by definition, there is a major inherent risk from overlooking disruptive technologies. That risk will manifest itself by the team not being very busy much longer as their work will go to people that have learned those new things.

A rising tide lifts all boats, and such is the case for many data science organizations says, Tim. The leaders that separate themselves in this environment are the ones that can couple the hard skills (i.e. statistics, programming, machine learning) with the soft skills (i.e. communication, empathy, collaboration). According to Tim, at CNA, the team works on both sets of skills every day so it can help provide a competitive advantage for Americas defense.

Dont forget about your people asserts Tim. He continues that CNA spends more of its waking hours working than spending those hours with families. Tim insists emerging data scientists do everything they can to help their people look forward to coming to work every day. Tim asks them to be the kind of leader that provides the psychological safety for people to share their ideas and problems with you. According to Tim, data scientists get better solutions and outcomes if they build an inclusive and learnable environment in their workplace, where their team will work as long and as hard as it takes to accomplish the mission. He concludes by saying, Mission first, people always.

More:

Tim Kao: Infusing Data Science to Revolutionize the Functionalities of Navy and Marine Industries - Analytics Insight

Read More..

This article was originally published here

Philos Trans A Math Phys Eng Sci. 2022 Jan 10;380(2214):20210127. doi: 10.1098/rsta.2021.0127. Epub 2021 Nov 22.

ABSTRACT

During the COVID-19 pandemic, more than ever, data science has become a powerful weapon in combating an infectious disease epidemic and arguably any future infectious disease epidemic. Computer scientists, data scientists, physicists and mathematicians have joined public health professionals and virologists to confront the largest pandemic in the century by capitalizing on the large-scale big data generated and harnessed for combating the COVID-19 pandemic. In this paper, we review the newly born data science approaches to confronting COVID-19, including the estimation of epidemiological parameters, digital contact tracing, diagnosis, policy-making, resource allocation, risk assessment, mental health surveillance, social media analytics, drug repurposing and drug development. We compare the new approaches with conventional epidemiological studies, discuss lessons we learned from the COVID-19 pandemic, and highlight opportunities and challenges of data science approaches to confronting future infectious disease epidemics. This article is part of the theme issue Data science approaches to infectious disease surveillance.

PMID:34802267 | DOI:10.1098/rsta.2021.0127

Excerpt from:

Data science approaches to confronting the COVID-19 pandemic: a narrative review - DocWire News

Read More..