Click here to close now.


Microservices Expo Authors: Greg O'Connor, Carmen Gonzalez, AppDynamics Blog, Elizabeth White, Ian Khan

Related Topics: @CloudExpo, Java IoT, Microservices Expo, Linux Containers, Containers Expo Blog, Cloud Security

@CloudExpo: Article

Real-Time Fraud Detection in the Cloud

Using machine learning agent ensembles

This article explores how to detect fraud among online banking customers in real-time by running an ensemble of statistical and machine learning algorithms on a dataset of customer transactions and demographic data. The algorithms, namely Logistic Regression, Self-Organizing Maps and Support Vector Machines, are operationalized using a multi-agent framework for real-time data analysis. This article also explores the cloud environment for real-time analytics by deploying the agent framework in a cloud environment that meets computational demands by letting users' provision virtual machines within managed data centers, freeing them from the worry of acquiring and setting up new hardware and networks.

Real-time decision making is becoming increasingly valuable with the advancement of data collection and analytics techniques. Due to the increase in the speed of processing, the classical data warehousing model is moving toward a real-time model. A platform that enables the rapid development and deployment of applications, reducing the lag between data acquisition and actionable insight has become of paramount importance in the corporate world. Such a system can be used for the classic case of deriving information from data collected in the past and also to have a real-time engine that reacts to events as they occur. Some examples of such applications include:

  • A product company can get real-time feedback for their new releases using data from social media
  • Algorithmic trading by reacting in real times to fluctuations in stock prices
  • Real-time recommendations for food and entertainment based on a customer's location
  • Traffic signal operations based on real-time information of volume of traffic
  • E-commerce websites can detect a customer transaction being authentic or fraudulent in real-time

A cloud-based ecosystem enables users to build an application that detects, in real-time, fraudulent customers based on their demographic information and financial history. Multiple algorithms are utilized to detect fraud and the output is aggregated to improve prediction accuracy.

The dataset used to demonstrate this application comprises of various customer demographic variables and financial information such as age, residential address, office address, income type, income frequency, bankruptcy filing status, etc. The dependent variable (the variable to be predicted) is called "bad", which is a binary variable taking the value 0 (for not fraud) or 1 (for fraud).

Using Cloud for Effective Usage of Resources
A system that allows the development of applications capable of churning out results in real-time has multiple services running in tandem and is highly resource intensive. By deploying the system in the cloud, maintenance and load balancing of the system can be handled efficiently. It will also give the user more time to focus on application development. For the purpose of fraud detection, the active components, for example, include:

  • ActiveMQ
  • Web services
  • PostgreSQL

This approach combines the strengths and synergies of both cloud computing and machine learning technologies, providing a small company or even a startup that is unlikely to have specialized staff and necessary infrastructure for what is a computationally intensive approach, the ability to build a system that make decisions based on historical transactions.

Agent Paradigm
As multiple algorithms are to be run on the same data, a real-time agent paradigm is chosen to run these algorithms. An agent is an autonomous entity that may expect inputs and send outputs after performing a set of instructions. In a real-time system, these agents are wired together with directed connections to form an agency. An agent typically has two behaviors, cyclic and triggered. Cyclic agents, as the name suggests, run continuously in a loop and do not need any input. These are usually the first agents in an agency and are used for streaming data to the agency by connecting to an external real-time data source. A triggered agent runs every time it receives a message from a cyclic agent or another triggered agent. Once it consumes one message, it waits for the next message to arrive.

Figure 1: A simple agency with two agents

In Figure 1, Agent 1 is a cyclic agent while Agent 2 is a triggered agent. Agent 1 finishes its computation and sends a message to Agent 2, which uses the message as an input for further computation.

Feature Selection and Data Treatment
The dataset used for demonstrating fraud detection agency has 250 variables (features) pertaining to the demographic and financial history of the customers. To reduce the number of features, a Random Forest run was conducted on the dataset to obtain variable importance. Next, the top 30 variables were selected based on the variable importance. This reduced dataset was used for running a list of classification algorithms.

Algorithms for Fraud Detection
The fraud detection problem is a binary classification problem for which we have chosen three different algorithms to classify the input data into fraud (1) and not fraud (0). Each algorithm is configured as a triggered agent for our real-time system.

Logistic Regression
This is a probabilistic classification model where the dependent variable (the variable to be predicted) is a binary variable or a categorical variable. In case of binary dependent variables favorable outcomes are represented as 1 and non-favorable outcomes are represented as 0. Logistic regression models the probability of the dependent variable taking the value 0 or 1.

For the fraud detection problem, the dependent variable "bad" is modelled to give probabilities to each customer of being fraud or not. The equation takes multiple variables as input and returns a value between 0 & 1 which is the probability of "bad" being 0. If this value is greater than 0.7, then that customer is classified as not fraud.

Self-Organizing Maps (SOM)
This is an artificial neural network that uses unsupervised learning to represent the data in lower (typically two dimensions) dimensions. This representation of the input data in lower dimensions is called a map. Like most artificial neural networks, SOMs operate in two modes: training and mapping. "Training" builds the map using input examples, while "mapping" automatically classifies a new input vector.

For the fraud detection problem, the input space which is a fifty dimensional space is mapped to a two dimensional lattice of nodes. The training is done using data from the recent past and the new data is mapped using the trained model, which puts it either in the "fraud" cluster or "not - fraud" cluster.

Figure 2: x is an in-put vector in higher dimension, discretized in 2D using wij as the weight matrix
Image Source:

Support Vector Machines (SVM)
This is a supervised learning technique used generally for classifying data. It needs a training dataset where the data is already classified into the required categories. It creates a hyperplane or set of hyperplanes that can be used for classification. The hyperplane is chosen such that it separates the different classes and the margin between the samples in the training set is widest.

For the fraud detection problem, SVM classifies the data points into two classes. The hyperplane is chosen by training the model over the past data. Using the variable "bad", the clusters are labeled as "0" (fraud) and "1" (not fraud). The new data points are classified using the hyperplane obtained while training.

Figure 3: Of the three hyperplanes which segment the data, H2 is the hyperplane which classifies the data accurately

Image Source:

Fraud Detection Agency
A four-tier agency is created to build a workflow process for fraud detection.

Streamer Agent (Tier 1): This agent streams data in real-time to agents in Tier 2. It is the first agent in the agency and its behavior is cyclic. It connects to a real-time data source, pre-processes the data and sends it to the agents in the next layer.

Algorithm Agents (Tier 2): This tier has multiple agents running an ensemble of algorithms with one agent per algorithm. Each agent receives the message from the streamer agent and uses a pre-trained (trained on historical data) model for scoring.

Collator Agent (Tier 3): This agent receives scores from agents in Tier 2 and generates a single score by aggregating the scores. It then converts the score into an appropriate JSON format and sends it to an UI agent for consumption.

User Interface Agent (Tier 4): This agent pushes the messages it receives to a socket server. Any external socket client can be used to consume these messages.

Figure 4: The Fraud detection agency with agents in each layer. The final agent is mapped to a port to which a socket client can connect

Results and Model Validation
The models were trained on 70% of the data and the remaining 30% of the data was streamed to the above agency simulating a real-time data source.

Under-sample: The ratio of number of 0s to the number of 1s in the original dataset for the variable "bad" is 20:1. This would lead to biasing the models towards 0. To overcome this, we sample the training dataset by under-sampling the number of 0s to maintain the ration at 10:1.

The final output of the agency is the classification of the input as fraudulent or not. Since the value for the variable "bad" is already known for this data, it helps us gauge the accuracy of the aggregated model.

Figure 5: Accuracy for detecting fraud ("bad"=1) for different sampling ratio between no.of 0s and no. of 1s in the training dataset

Fraud detection can be improved by running an ensemble of algorithms in parallel and aggregating the predictions in real-time. This entire end-to-end application was designed and deployed in three working days. This shows the power of a system that enables easy deployment of real-time analytics applications. The work flow becomes inherently parallel as these agents run as separate processes communicating with each other. Deploying this in the cloud makes it horizontally scalable owing to effective load balancing and hardware maintenance. It also provides higher data security and makes the system fault tolerant by making processes mobile. This combination of a real-time application development system and a cloud-based computing enables even non-technical teams to rapidly deploy applications.


  • Gravic Inc, "The Evolution of Real-Time Business Intelligence", ""
  • Bernhard Schlkopf, Alexander J. Smola ( 2002), "Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond (Adaptive Computation and Machine Learning)", MIT Press​
  • Christopher Burges (1998), "A Tutorial on Support Vector Machines for Pattern Recognition", Data Mining and Knowledge Discovery, Kluwer Publishers
  • Kohonen, T. (Sep 1990), "The self-organizing map", Proceedings of IEEE
  • Rokach, L. (2010). "Ensemble based classifiers". Artificial Intelligence Review
  • Robin Genuer, Jean-Michel Poggi, Christine Tuleau-Malot, "Variable Selection using Random Forests",

More Stories By Roger Barga

Roger Barga, PhD, is Group Program Manager for the CloudML team at Microsoft Corporation where his team is building machine learning as a service on the cloud. He is also a lecturer in the Data Science program at the University of Washington. Roger joined Microsoft in 1997 as a Researcher in the Database Group of Microsoft Research (MSR), where he was involved in a number of systems research projects and product incubation efforts, before joining the Cloud and Enterprise Division of Microsoft in 2011.

More Stories By Avinash Joshi

Avinash Joshi is a Senior Research Analyst in the Innovation and Development group of Mu Sigma Business Solutions. He is currently part of a team that works on generating insights from real-time data streams in financial markets. Avinash joined this team in 2011 and has interests ranging from marketing mix modeling to algorithmic trading.

More Stories By Pravin Venugopal

Pravin Venugopal is a Senior Research Analyst in the Innovation and Development group of Mu Sigma Business Solutions. He is currently part of a team that is developing a low latency platform for algorithmic trading. Pravin received his Masters degree in Computer Science and has been a part of Mu Sigma since 2012. His interests include analyzing real-time financial data streams and algorithmic trading.

Comments (1)

Share your thoughts on this story.

Add your comment
You must be signed in to add a comment. Sign-in | Register

In accordance with our Comment Policy, we encourage comments that are on topic, relevant and to-the-point. We will remove comments that include profanity, personal attacks, racial slurs, threats of violence, or other inappropriate material that violates our Terms and Conditions, and will block users who make repeated violations. We ask all readers to expect diversity of opinion and to treat one another with dignity and respect.

@MicroservicesExpo Stories
It's been a busy time for tech's ongoing infatuation with containers. Amazon just announced EC2 Container Registry to simply container management. The new Azure container service taps into Microsoft's partnership with Docker and Mesosphere. You know when there's a standard for containers on the table there's money on the table, too. Everyone is talking containers because they reduce a ton of development-related challenges and make it much easier to move across production and testing environm...
Internet of @ThingsExpo, taking place June 7-9, 2016 at Javits Center, New York City and Nov 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA, is co-located with the 18th International @CloudExpo and will feature technical sessions from a rock star conference faculty and the leading industry players in the world and ThingsExpo New York Call for Papers is now open.
With major technology companies and startups seriously embracing IoT strategies, now is the perfect time to attend @ThingsExpo 2016 in New York and Silicon Valley. Learn what is going on, contribute to the discussions, and ensure that your enterprise is as "IoT-Ready" as it can be! Internet of @ThingsExpo, taking place Nov 3-5, 2015, at the Santa Clara Convention Center in Santa Clara, CA, is co-located with 17th Cloud Expo and will feature technical sessions from a rock star conference faculty ...
We are rapidly moving to a brave new world of interconnected smart homes, cars, offices and factories known as the Internet of Things (IoT). Sensors and monitoring devices will touch every part of our lives. Let's take a closer look at the Internet of Things. The Internet of Things is a worldwide network of objects and devices connected to the Internet. They are electronics, sensors, software and more. These objects connect to the Internet and can be controlled remotely via apps and programs. ...
The Internet of Things (IoT) is growing rapidly by extending current technologies, products and networks. By 2020, Cisco estimates there will be 50 billion connected devices. Gartner has forecast revenues of over $300 billion, just to IoT suppliers. Now is the time to figure out how you’ll make money – not just create innovative products. With hundreds of new products and companies jumping into the IoT fray every month, there’s no shortage of innovation. Despite this, McKinsey/VisionMobile data...
Just over a week ago I received a long and loud sustained applause for a presentation I delivered at this year’s Cloud Expo in Santa Clara. I was extremely pleased with the turnout and had some very good conversations with many of the attendees. Over the next few days I had many more meaningful conversations and was not only happy with the results but also learned a few new things. Here is everything I learned in those three days distilled into three short points.
One of the most important tenets of digital transformation is that it’s customer-driven. In fact, the only reason technology is involved at all is because today’s customers demand technology-based interactions with the companies they do business with. It’s no surprise, therefore, that we at Intellyx agree with Patrick Maes, CTO, ANZ Bank, when he said, “the fundamental element in digital transformation is extreme customer centricity.” So true – but note the insightful twist that Maes adde...
DevOps is about increasing efficiency, but nothing is more inefficient than building the same application twice. However, this is a routine occurrence with enterprise applications that need both a rich desktop web interface and strong mobile support. With recent technological advances from Isomorphic Software and others, rich desktop and tuned mobile experiences can now be created with a single codebase – without compromising functionality, performance or usability. In his session at DevOps Su...
Using any programming framework to the fullest extent possible first requires an understanding of advanced software architecture concepts. While writing a little client-side JavaScript does not necessarily require as much consideration when designing a scalable software architecture, the evolution of tools like Node.js means that you could be facing large code bases that must be easy to maintain.
As organizations realize the scope of the Internet of Things, gaining key insights from Big Data, through the use of advanced analytics, becomes crucial. However, IoT also creates the need for petabyte scale storage of data from millions of devices. A new type of Storage is required which seamlessly integrates robust data analytics with massive scale. These storage systems will act as “smart systems” provide in-place analytics that speed discovery and enable businesses to quickly derive meaningf...
You may have heard about the pets vs. cattle discussion – a reference to the way application servers are deployed in the cloud native world. If an application server goes down it can simply be dropped from the mix and a new server added in its place. The practice so far has mostly been applied to application deployments. Management software on the other hand is treated in a very special manner. Dedicated resources are set aside to run the management software components and several alerting syst...
Culture is the most important ingredient of DevOps. The challenge for most organizations is defining and communicating a vision of beneficial DevOps culture for their organizations, and then facilitating the changes needed to achieve that. Often this comes down to an ability to provide true leadership. As a CIO, are your direct reports IT managers or are they IT leaders? The hard truth is that many IT managers have risen through the ranks based on their technical skills, not their leadership ab...
People want to get going with DevOps or Continuous Delivery, but need a place to start. Others are already on their way, but need some validation of their choices. A few months ago, I published the first volume of DevOps and Continuous Delivery reference architectures which has now been viewed over 50,000 times on SlideShare (it's free to registration required). Three things helped people in the deck: (1) the reference architectures, (2) links to the sources for each architectur...
Hiring the wrong candidate can cost a company hundreds of thousands of dollars, and result in lost profit and productivity during the search for a replacement. In fact, the Harvard Business Review has found that as much as 80 percent of turnover is caused by bad hiring decisions. But when your organization has implemented DevOps, the job is about more than just technical chops. It’s also about core behaviors: how they work with others, how they make decisions, and how those decisions translate t...
Continuous processes around the development and deployment of applications are both impacted by -- and a benefit to -- the Internet of Things trend. To help better understand the relationship between DevOps and a plethora of new end-devices and data please welcome Gary Gruver, consultant, author and a former IT executive who has led many large-scale IT transformation projects, and John Jeremiah, Technology Evangelist at Hewlett Packard Enterprise (HPE), on Twitter at @j_jeremiah. The discussion...
The Internet of Things is clearly many things: data collection and analytics, wearables, Smart Grids and Smart Cities, the Industrial Internet, and more. Cool platforms like Arduino, Raspberry Pi, Intel's Galileo and Edison, and a diverse world of sensors are making the IoT a great toy box for developers in all these areas. In this Power Panel at @ThingsExpo, moderated by Conference Chair Roger Strukhoff, panelists discussed what things are the most important, which will have the most profound...
In today's enterprise, digital transformation represents organizational change even more so than technology change, as customer preferences and behavior drive end-to-end transformation across lines of business as well as IT. To capitalize on the ubiquitous disruption driving this transformation, companies must be able to innovate at an increasingly rapid pace. Traditional approaches for driving innovation are now woefully inadequate for keeping up with the breadth of disruption and change facin...
Discussions of cloud computing have evolved in recent years from a focus on specific types of cloud, to a world of hybrid cloud, and to a world dominated by the APIs that make today's multi-cloud environments and hybrid clouds possible. In this Power Panel at 17th Cloud Expo, moderated by Conference Chair Roger Strukhoff, panelists addressed the importance of customers being able to use the specific technologies they need, through environments and ecosystems that expose their APIs to make true ...
PubNub has announced the release of BLOCKS, a set of customizable microservices that give developers a simple way to add code and deploy features for realtime apps.PubNub BLOCKS executes business logic directly on the data streaming through PubNub’s network without splitting it off to an intermediary server controlled by the customer. This revolutionary approach streamlines app development, reduces endpoint-to-endpoint latency, and allows apps to better leverage the enormous scalability of PubNu...
In his General Session at DevOps Summit, Asaf Yigal, Co-Founder & VP of Product at, explored the value of Kibana 4 for log analysis and provided a hands-on tutorial on how to set up Kibana 4 and get the most out of Apache log files. He examined three use cases: IT operations, business intelligence, and security and compliance. Asaf Yigal is co-founder and VP of Product at log analytics software company In the past, he was co-founder of social-trading platform Currensee, which...