Tag Archives: Behavioral

Behavioral Analytics Attack Fraud, Cyber and Financial Crime

Analytics Hand Behavioral Analytics Attack Fraud, Cyber and Financial Crime

Economies of scale is one of my favorite economic principles. It’s especially cool to see how FICO customers can realize associated benefits by using our behavioral analytic technology.

IDC predicts that in 2017, behavioral analytics across compliance, fraud, and cyber detection and prevention will be in place at 15% of banks, helping them to avoid losses, regulatory fines and sanctions.

Banks have already made a big start in the fraud space. FICO introduced behavioral analytics in the early 1990s and we currently analyze two-thirds of the world’s payment card transactions, in real time, for fraud.

Now, FICO’s proven behavioral analytics can be applied by forward-thinking institutions to fight a wide range of financial crimes. In doing so, banks can gain powerful technology economies of scale, too, leveraging mature, market-proven analytic models to benefit new domains within their business.

How do behavioral analytics work?  

A quick search may tell you that “behavioral analytics” measure the behavior of consumers on ecommerce platforms, online games, web and mobile applications or Internet of Things (IoT) devices. In fact, “behavioral analytics,” from a pure data science point of view, help us to understand much more:

  1. what an individual person or device does, and
  2. what they don’t do, but might in the future.

The first comparison is of the customer or device in the context of their own history of events, where one can determine changes from historical behaviors. A second comparison is done by grouping customers or devices into similar clusters, and then analyzing how much the behaviors of individuals deviate from their associated groups.

Depending on the degree of variance, we can assess how likely the behavior is to be aberrant and thus potentially fraudulent or criminal — or, in the case of a network device, how likely that endpoint is to have been compromised by a cyber attacker.

Power at scale: Enhancing fraud, compliance and cyber security defenses 

Behavioral analytics are a mature technology in fraud prevention. Behavioral analytics technology allows us to flag potentially fraudulent transactions with pinpoint accuracy, greatly reducing the volume of “false positives,” or transactions flagged as potentially fraudulent that are, in fact, legitimate. FICO has honed its fraud detection technology to identify the needles in the haystack.

In terms of compliance — particularly anti-money laundering (AML) and terrorism financing — the most prevalent transaction monitoring solutions used to identify illicit activity in these domains are extremely imprecise. The compliance solutions generate tens of thousands of alerts for every genuinely criminal transaction requiring a formal suspicious activity report (SAR). The volume is so great that that compliance officers can only investigate a small fraction of suspected SARs. As a result, illegal transactions slip through, continuing through the global payments system.

It’s the same situation with cybersecurity. In any security operations center, there’s a cacophony of alarms, 24-7. It’s impossible for operators to tell which alarms are calling out truly meaningful intrusions, and which are just noise. That’s why so many cyber attacks go undetected for weeks, months or even years.

FICO solutions for compliance and cybersecurity address these shortcomings, dramatically improving the accuracy of AML detection and enabling real-time discovery of cyber threats.

Benefits beyond cost savings

As IDC noted, behavioral analytics technology can help financial institutions to avoid regulatory fines and sanctions. The benefits extend farther: in terms of fraud and compliance, behavioral analytics will allow more illicit transactions to be stopped as they occur, saving untold amounts of financial and reputational loss.

With regard to cybersecurity, the ability to pinpoint cyber attacks more quickly greatly reduces the “dwell time” of malware, ransomware and other malicious code that causes data breaches and other damage. Again, this can significantly reduce the costs of remediation that result from breaches, as well as major financial and reputational losses.

Want to know more? Check out my latest FICO Hot Topic Q&A, “Behavioral Analytics: Boosting Protection across Fraud, Compliance and Cybersecurity.” Follow me on Twitter, too, @ScottZoldi to keep up with my latest analytics rants, raves and musings.

Let’s block ads! (Why?)


Teradata’s Customer Journey Analytic Solution Creates Behavioral Insights to Deliver a Distinct Customer Experience

Data Science meets marketing as companies connect interactions to ensure a personalized and relevant customer journey

Teradata (NYSE: TDC), a leading analytics solutions company, today announced the Teradata Customer Journey Analytic Solution, a complete set of capabilities for discerning the behavioral paths of each individual customer, determining the next best interaction and delivering a consistent, personalized brand experience through every channel and touch point. The solution uses Teradata’s proven consulting services, as well as technologies that enable real-time customer data integration, advanced behavioral analytics and multi-channel marketing automation. It enables CMOs who want to truly understand each individual customer experience to move beyond old school one-to-one marketing tactics that rely on purchases and traditional customer profiling. The insights resulting from Teradata’s Customer Journey Analytic Solution enable marketers to optimize objectives such as response and conversion rates, service delivery, churn, and customer satisfaction – leading directly to high-impact business outcomes such as increased revenue and customer retention.

Customers today require every interaction with a brand to be consistent, but also personalized and relevant. This is despite the ever-expanding range of channels that make building a complete picture of each individual customer extremely challenging. Delivering a better customer experience requires the integration of data from all customer touch-points, whether online or offline, and often in real time. In practice, most companies struggle to blend the technologies and siloed data to understand, anticipate and engage each individual customer holistically.

“Managing every customer as an individual, based on their interactions with your company, requires not only the integration of different types of data but understanding it through the application of complex multi-genre analytics. Even the best-known companies feel this is a ‘boil the ocean’ project – making sense of billions of events for millions of customers, in real time. This challenging situation is where Teradata alone thrives,” said Dan Harrington, EVP, Consulting and Support Services, Teradata Corporation. “Our Customer Journey Analytic Solution is the embodiment of Teradata’s proven experience in the field with some of the world’s largest and most innovative customer-centric companies. It gives marketers a comprehensive view of their customers, based on each person’s individual interactions, so that they can provide the right help at the right time.”

Gartner Research says that by 2018, organizations that have fully invested in all types of online personalization will outsell companies that have not by 30 percent. According to the research firm, key areas of differentiation between vendors include the channels on which the solutions focus, the manner in which seemingly anonymous interactions are stitched together, the tools in place to provide visualization of journeys, and the outputs to other systems.

“With Teradata we were able to accurately combine detailed customer interactions and tie them back to a unique customer identifier in Teradata,” said Alick Rocca, Head of Management Information/Business Intelligence, JD Williams. “Teradata Aster Analytics helped us see the bigger picture within this connected data. For example, we found customers would use a mobile device to browse, then come back and purchase through another channel later. Insights like this helped generate better marketing attribution models to make smarter decisions about how we advertise, generating return on our marketing investment.”

The typical experience for companies using Teradata’s Customer Journey Analytic Solution is:

Teradata customer journey Teradata’s Customer Journey Analytic Solution Creates Behavioral Insights to Deliver a Distinct Customer Experience

¹“Market Guide for Customer Journey Analytics” published June 9, 2016 by analysts Jason Daigler, Brian Manusama, Gareth Herschel, Jim Davies and Shubhangi Vashisth

The Teradata Customer Journey Analytic Solution accomplishes this using the following capabilities:

Intelligently Integrating Data in Real Time

  • Provides a complete view of each individual customer by integrating their data regardless of where the data is generated or stored
  • Captures digital and offline interactions, from the Web, mobile or payment systems, in real time
  • Combines distributed data, from the cloud, the data lake and the data warehouse
  • Accepts new data, channels and campaigns quickly and easily

Multi-genre Analytics

  • Enables a wide range of advanced predictive, descriptive and prescriptive analytic techniques, with machine learning for real-time decisioning
  • Allows marketers to utilize these advanced analytic solutions, regardless of where their data lives
  • Stitches together customer events using pathing analytics to give marketers a unique behavioral view of each customer – augmenting the traditional customer profile with personalized, individual messages that help customers achieve their goals

Interaction Management

  • Delivers multi-channel campaign management capability with real time-decisioning and automation that scales for both volume and communication type
  • Provides sophisticated and flexible customer segmentation, customer journey planning and decisioning capabilities
  • Supports open source technology that allows for the incorporation of data from any source to drive decisions, and integration with any inbound or outbound channel (including digital)
  • Empowers marketing leaders to also drive key improvements on processes and tools to ensure maximum productivity of the marketing efforts

Each of these capabilities enhances a company’s capacity to flex and scale as the business grows. The Teradata Customer Journey Analytic Solution scales to support increasing volumes of data, more analytic models and progression in the myriad of ways a growing customer base will engage with the brand via new channels.

Teradata’s Customer Journey Analytic Solution is available immediately.

Relevant News Links

Let’s block ads! (Why?)

Teradata United States

Unlock Behavioral Insight from MongoDB

Recently Tom () and I had the chance to work together with Amanda Shiga () from Nonlinear Digital to build web analytics process using RapidMiner. Amanda has an on-going pilot project to apply data mining techniques to clickstream and user behavior data collected from her client’s website. The website has a number of value-weighted micro-conversions, such as newsletter signup, or downloading a whitepaper, or event registration. For online retailers, seeing the visitors convert to paying customers is the ultimate goal. The focus of web analytics nowadays has shifted from getting visitors to a website to turning the web visitors into high value customers. Armed with advanced data collection methods and machine learning approaches, RapidMiner can help website owners to measure the successes of their online business goals.

Environment: RapidMiner 7.2, MongoDB

Collecting the Data from MongoDB

Amanda’s web analytics project presented us with a classic “big data” problem. The granular details of the visitors activities are originally stored in a NoSQL database. MongoDB captured many differente attributes of user behavior, so the following analytics ETL process needs to handle a wide variety of data structures.  This data was coming in at a high velocity from thousands of concurrent users so we have to deal with large volumns of data generated by monitoring user activity tracking how content is consumed and interactions are occurring on the website.

Snapshot of the raw data in MongoDB:

yy mongodb 1 300x171 Unlock Behavioral Insight from MongoDB

As you can see from the Robomongo interface, some features like the visitors’ browser type, referring site (google, bing, etc), clickstreams and viewed pages are all recorded in the unstructured format. We have to first set up the connection to integrate MongoDB account with RapidMiner Studio and then massage the data into the good structures. Using ‘Manage Connections’ from the menu bar of RapidMiner Studio, the users can add a new connection to their own MongoDB.

yy mongodb 2 300x219 Unlock Behavioral Insight from MongoDB

yy mongodb 3 Unlock Behavioral Insight from MongoDB

Among millions of cloud connectors and data (database) connectors, ‘Read MongoDB’ operator can be used to pull raw data from a predefined MongoDB instance to RapidMiner Studio. Just make sure the free NoSQL Connectors extension is downloaded and installed from RapidMiner Marketplace.

yy mongodb 4 300x100 Unlock Behavioral Insight from MongoDB

Ok. After the connections and preparations are all set, let’s load the data from MongoDB, and apply ‘Loop Collection’ to the retrieved collection of documents.

yy mongodb 5 300x84 Unlock Behavioral Insight from MongoDB

Because the output from MongoDB will be a collation of JSON documents (example of JSON document). What we can do inside the loop for each document is to add a converter ‘JSON to data’ right after the JSON document input to flatten and transform single JSON document into one structured example set.

In case you have some content in the JSON file that cannot be easily transformed, for example data stored via GridFS as ‘<Binary Data>’, we can use ‘Remove Document Parts’ to clean up some unexpected special characters from JSON file.

yy mongodb 7 300x90 Unlock Behavioral Insight from MongoDB

So far we have successfully load the visitors’ activities from MongoDB and transformed them to the nice structured format.

yy mongodb 8 300x26 Unlock Behavioral Insight from MongoDB

But it is still early that the collected example sets generated by ‘JSON to Data’ are not ready for appending or modelling, because the example sets are not in the same format. We need some data preprocessing to standardize the visitors’ profiles.

yy mongodb 9 300x25 Unlock Behavioral Insight from MongoDB

Data Preprocessing

Recall that in the last two snapshots, the number of attributes for two visitor’s profile are not same (72 vs 81), meaning that some visitors may visit more webpages and there could be more children information for detailed page view. It is possible that some visitors have a valid ‘Campaign ID’ while others don’t have such attribute for Campaign ID. How to add the columns back if the important features are missing in the original visitors’ profile? Here we did some tricks to perform a ‘Transpose’ of the data and created a set of tags for indicating whether a target attribute is found or not. Then we use a set of Macros to deliver values of the indicators to the downstream. Here is the quick view for the sub-process built for checking a high value attribute is available or not.

yy mongodb 10 300x101 Unlock Behavioral Insight from MongoDB

The next step in my data preprocessing would be adding the important attributes if missing. We will use several branches, in the following sub-process. Inside the ‘Branch’ we simply apply ‘Generate Attribute’ if macro value indicates that the target attribute is missing.

yy mongodb 11 300x120 Unlock Behavioral Insight from MongoDB

After that we could match some keywords with the URL path, and extract how much time spent on each page view. Here a ‘De-Pivot’ is a suitable solution for that, because the exact total page views for individual visitor are unknown. We will create one line for each clicked URL path and later match it with a list of high value keywords.

yy mongodb 12 300x129 Unlock Behavioral Insight from MongoDB

Some data blending tricks to convert the data types (e.g. convert numerical to binomial, parse strings to numbers, ‘nominal to numerical’ for dummy coding categorical variables, etc.) may be needed. Please be aware that in RapidMiner some supervised learning algorithms can handle either nominal or numerical variable, but some algorithms are only compatible with numerical variables. Keep in mind that always double check the data types for all variables before fitting any models!

Classification or Regression?

If you have a numerical target for prediction, e.g. Exact value of the profile, we will build regression models. If you want to predict a binomial target, e.g. High or Low value customer, Converted or Not Converted visitor, it becomes a binomial classification problem.

yy mongodb 13 300x58 Unlock Behavioral Insight from MongoDB

The newly added operators in RapidMiner 7.2, Generalized Linear Model or Gradient Boosted Trees are so powerful that are capable to handle both numerical and nominal variables, and can be used to build either regression or classification models. A quick and dirty GLM is built inside a 5-fold cross-validation within one minute in RapidMiner. We easily achieved >76% average accuracy and 0.85 AUC on the testing set.

Reincorporate the Prediction Back into Marketing

yy mongodb 14 300x124 Unlock Behavioral Insight from MongoDB

The scoring results sometimes make people think how to make marketing efforts to direct those non-converted visitors who have extremely high confidence level of conversion. Are there any leaks from the first clicks that stopped a visitor from signing up a newsletter? Which search engine and search keywords drives the most traffic and creating the most conversions? Some online efforts including email campaigns, adding banner ads, personalized interface are optimization strategies to get more conversions and improve the online business. By understanding visitor behavior, the website owner can have more than just a presence on the web. They can have a successful growing business.

Download RapidMiner Studio

The free version of our RapidMiner Studio 7.2 now includes functionality that was previously only available in the commercial version, for example, connectors to commercial databases. All the features of our RapidMiner platform are now available to EVERYONE. Let us get started from the download page to unlock your business values from big data.

Let’s block ads! (Why?)