Applications, Behavior Learning and the Personal Touch
January 18, 2012
David Williams and Leslie Minnix-Wolfe
Share this

Though online businesses can’t offer the same sort of “human touch” as the staff at a brick-and-mortar store, they can go quite a long way toward personalizing and improving the end-user’s experience. End-user behavior learning technology provides the business with a view into how each end-user interacts with their online business services to ensure a superior user experience.

The business learns about user experiences based on past online activity, and quickly and proactively adjusts to meet expected levels of service regardless of the conditions or variables, such as for online shopping during the holiday season, when traffic peaks on many sellers’ websites.

Behavior Learning: The Key to Positive Customer Experiences

Superior, personalized online experiences happen because technology enables the business to deliver desired results based on learned behavior. IT has its own model and technology to identify “abnormal” behavior of applications and systems that affect the user’s experience and behavior. End-user behavior learning tells IT (and application owners) about each person using a specific technology or application and how the application performance affects the user’s actions.

Tools support end-user and application learning by leveraging statistical process control to gather data from multiple sources, establish patterns of behavior, and proactively detect subtle changes in that behavior. If you can monitor end-user and application behavior, and establish norms, then you can more proactively detect a performance issue. The technology can determine the impact on users and the business, isolate the cause of the problem, and drive corrective actions.

Behavior learning technology understands the systems, detects deviations from normal behavior, and provides fewer, earlier, and more accurate alerts. For example, a sluggish response time is a clear indicator that something is “misbehaving” in your infrastructure. End-user behavior learning technology tells you the expected response time based on the time of day, the day of week, load on the system, location of the user, and so on.

By understanding the expected behavior of the applications under various conditions, you can detect a slowdown before a user calls the help desk or abandons your site. You can also quickly assess the impact of new or modified application features, and changes in user traffic or system configurations.

The Starting Point: Behavior Monitoring

By monitoring and learning the normal behavior of your applications and your end users, you can understand what and how elements are being accessed and who is accessing them. If a change in end-user behavior occurs at the time of a slowdown, an alert is generated to notify an administrator or operator. By monitoring user and application behavior and establishing the norms for any given time period, you can proactively determine when changes occur in performance or behavior over time.

Real and “Synthetic” Users
End-user monitoring should extend to both the real user and the “synthetic” user. With synthetic transactions, you can simulate types of actions — setting up critical user scenarios and running them repeatedly to establish a baseline for comparing the performance for that same series of steps from one hour or day to the next. This is especially useful for assessing the availability of key scenarios and determining whether changes to the application or to the environment in which it runs will affect the end-user experience.

When combined with “real” user monitoring, you can determine if performance is impacted by other criteria, such as the volume or location of users, the actions the user takes, the use of mobile or non-mobile devices, or by a change in the application or environment that modifies or introduces new critical user scenarios.

Speed Matters
Advanced application performance monitoring solutions detect problems based on real end-user response times as soon as a single user begins to experience them, capturing all the data necessary to quickly prioritize, diagnose, and resolve the problems. You can know what problems are likely to impact your users and how to prioritize and assign them based on the issue source and the potential criticality and severity of user and business impact. Behavior learning solutions evaluate this data, identifying behavioral patterns so that you know when application response times and the end-user experiences are becoming slower ― or faster ― than usual.

End-User Behavior as a Source of Business Information

If a slowdown occurs in the volume of transactions completed, you can correlate that type of business information to the end-user and application response times. You can quickly determine if there is a potential problem and proactively investigate the issue. The performance of all the individual service components may appear to be satisfactory. Yet combined the services being delivered may not be performing satisfactorily to the end user. This combination gives you awareness of the experience and the potential impact on your business.

Monitoring Your Services in the Cloud
Understanding the real user experience is essential for monitoring your services in the cloud. In the cloud, you don’t always have access to the infrastructure and applications being delivered. If, however, you monitor the real user experience when trying to access the cloud, then you have a better sense of whether you and your customers are getting the service you paid for and expect.

More than Just a “Nice Touch”

Behavior-learning technology observes behavior with the goal of providing a positive customer experience. The technology empowers you to do a better job of identifying the root cause of problems and resolving application and infrastructure issues before they impact critical business services. The result will be greater customer satisfaction and loyalty, as well as an increased ability to attract new customers.

About David Williams

David Williams is a Vice President of Strategy in the Office of the CTO, with particular focus on availability and performance monitoring, applications performance monitoring, IT operations automation, and management tools architectures. He has 29 years of experience in IT operations management. Williams joined BMC from Gartner, where he was Research VP, leading the research for IT process automation (run book automation); event correlation and analysis; performance monitoring; and IT operations management architectures and frameworks. His past experience also includes executive-level positions at Alterpoint (acquired by Versata), IT Masters (acquired by BMC Software), and as vice president of Product Management and Strategy at IBM Tivoli. He also worked as a Sr. Technologist at CA for Unicenter TNG and spent his early years in IT working in computer operations for several companies, including Bankers Trust.

About Leslie Minnix-Wolfe

Leslie Minnix-Wolfe is the Lead Solutions Marketing Manager for Proactive Operations and Application Performance Management solutions at BMC Software. Minnix-Wolfe has more than 25 years of diverse development and marketing experience, primarily in the IT systems management domain, with a broad base of experience, especially in Business Service Management and predictive analytics. She previously held product and development management positions at several high-tech start-ups, including Netuitive and Managed Objects.

Share this

The Latest

July 18, 2019

Organizations that are working with artificial intelligence (AI) or machine learning (ML) have, on average, four AI/ML projects in place, according to a recent survey by Gartner, Inc. Of all respondents, 59% said they have AI deployed today ...

July 17, 2019

The 11th anniversary of the Apple App Store frames a momentous time period in how we interact with each other and the services upon which we have come to rely. Even so, we continue to have our in-app mobile experiences marred by poor performance and instability. Apple has done little to help, and other tools provide little to no visibility and benchmarks on which to prioritize our efforts outside of crashes ...

July 16, 2019

Confidence in artificial intelligence (AI) and its ability to enhance network operations is high, but only if the issue of bias is tackled. Service providers (68%) are most concerned about the bias impact of "bad or incomplete data sets," since effective AI requires clean, high quality, unbiased data, according to a new survey of communication service providers ...

July 15, 2019

Every internet connected network needs a visibility platform for traffic monitoring, information security and infrastructure security. To accomplish this, most enterprise networks utilize from four to seven specialized tools on network links in order to monitor, capture and analyze traffic. Connecting tools to live links with TAPs allow network managers to safely see, analyze and protect traffic without compromising network reliability. However, like most networking equipment it's critical that installation and configuration are done properly ...

July 11, 2019

The Democratic presidential debates are likely to have many people switching back-and-forth between live streams over the coming months. This is going to be especially true in the days before and after each debate, which will mean many office networks are likely to see a greater share of their total capacity going to streaming news services than ever before ...

July 10, 2019

Monitoring of heating, ventilation and air conditioning (HVAC) infrastructures has become a key concern over the last several years. Modern versions of these systems need continual monitoring to stay energy efficient and deliver satisfactory comfort to building occupants. This is because there are a large number of environmental sensors and motorized control systems within HVAC systems. Proper monitoring helps maintain a consistent temperature to reduce energy and maintenance costs for this type of infrastructure ...

July 09, 2019

Shoppers won’t wait for retailers, according to a new research report titled, 2019 Retailer Website Performance Evaluation: Are Retail Websites Meeting Shopper Expectations? from Yottaa ...

June 27, 2019

Customer satisfaction and retention were the top concerns for a majority (58%) of IT leaders when suffering downtime or outages, according to a survey of top IT leaders conducted by AIOps Exchange. The effect of service interruptions on customers outweighed other concerns such as loss of revenue, brand reputation, negative press coverage, or the impact on IT Ops teams.

June 26, 2019

It is inevitable that employee productivity and the quality of customer experiences suffer as a consequence of the poor performance of O365. The quick detection and rapid resolution of problems associated with O365 are top of mind for any organization to keep its business humming ...

June 25, 2019

Employees at British businesses rate computer downtime as the most significant irritant at their current workplace (41 percent) when asked to pick their top three ...