The stands have emptied. The Broncos and the Panthers played a great game. And of course, Lady Gaga just might have been the best musical performance during the game…and possibly ever…I digress… Now that the confetti has settled, advertisers are eagerly reviewing the data to see if they hit their goals. With spots running in the millions, advertising during the biggest game of the year is no pee-wee sport. The Second Screen Phenomenon Strikes Again In our post last week, we discussed our client, Wix, and the second screen phenomenon during their 2015 Super Bowl ad campaign. During last year’s Super Bowl Wix saw a huge spike (a.k.a. an anomaly) of traffic when their ad aired on television. The data we examined proved that people actually watched and reacted to the ads by accessing the Web on a second device. So how did they fare this year? Second Screen Behavior Continues For the second year in a row, Wix came out a winner. Below is a graph showing the days leading up to the Super Bowl and the actual day of the game. Note the fairly regular seasonal pattern as the traffic goes up and down each day. Slide your eyes to the right and you can clearly see the spike in traffic. While the Anodot anomaly detection system correlated 240 (!) different application metrics with simultaneous anomalies, the two metrics shown here show jumps of more than 900% in one case, and more than 1000% in the other. In other words, a huge jump in traffic all over the site, including the sign-up page. Note that the anomaly score for this traffic spike is 98, that is, 98 out of 100. In other words, not just a hop, but a huge, massive jump, worth taking note of, and a huge jump across hundreds of tracked metrics. Now what about the second screen phenomenon that we witnessed last year? Sure enough, people are browsing from the closest thing at hand; mobile and tablet browsing to the Wix site jumped by 150% when their ad aired, while browsing from traditional PC “merely” doubled. Digital receivers, i.e. people browsing right from their TVs, while still only accounting for a tiny fraction of total traffic (so small, in fact, that you can barely see it on the graph below), saw a 1000% increase. A Winning Campaign With regard to last year, Wix’s VP Marketing Omer Shai said in an interview with Fortune: “We did pretty good in terms of the amount of money we got back from the campaign we did. It gave us great confidence in doing it [another Super Bowl ad] again.” What’s great for Wix is that since they are a web-based business, with optimized pages they can immediately convert a large portion of their Super Bowl traffic into business. These traffic results are on par with what any advertiser could hope for following a large scale campaign like this. So…who’s going for an advertising touchdown in 2017?

A brief brochure about how to use Anodot to receive immediate alerts when things go wrong in factories, industrial settings and connected cars and buildings.

Everyone knows that scoring ad time during the Super Bowl is a turning point for any business. The Super Bowl is, perhaps, the pinnacle of advertising. Many have wondered, though, if the high ticket price and the effort to create a spectacular ad is actually worth it. Companies pull out all the stops. They push all boundaries and spare no cost. But is it really worth it? Do those ads actually drive traffic? Wix, the cloud-based website development platform and an Anodot customer, ran an ad during last year’s Super Bowl and are looking forward to making waves with a new ad slot this year when the Panthers meet the Broncos. We took a look at the metrics Wix sends to Anodot for anomaly detection, and sure enough, during the 2015 Super Bowl there was indeed a huge spike (a.k.a. an anomaly) of traffic to Wix. As you can see based on the huge jump in the screenshot below, people actually are watching and reacting to the ads. They’re not just watching the ads so they can compare notes at the watercooler the next day, they’re actually paying attention and reacting. The most traffic  came from mobile devices, which reinforces the notion of a second screen phenomenon. Consumers are literally glued to their screens…multiple screens…and seamlessly move from one to the other. See an ad that sparks an interest? Consumers will look away from the television, pick up their mobile device and respond. In Wix's case, we saw a direct correlation in the air time and content consumption. “We’ve seen a direct impact from the Super Bowl,” said Doron Ben David, CTO of Uprise, an advertising platform and another Anodot customer. “In past games, traffic to our networks went down since people were busy watching the game, and then it increased significantly during the ads. Viewers are consuming content on multiple devices and interacting between them.” So what will Super Bowl 50 bring for advertisers and viewers this coming Sunday besides Wix's adorable upcoming Kung Fu Panda ad? We look forward to seeing the results in real time as we cheer from the sidelines.  

A brief brochure about increasing business control with real time business incident detection, anomaly detection and analytics.

O’Reilly Data’s Ben Lorica interviews Anodot Co-Founder and Chief Data Scientist Dr. Ira Cohen about the challenges in building an advanced analytics system for intelligent applications at extremely large scale.

In a new article on DevOps.com, Chris Riley reviews how Internet leader Wix, leveraging machine learning for full visibility, monitors its complex DevOps environment with Anodot. Wix Achieves Proactive Monitoring with Anodot's Machine Learning Challenge: Leading website builder Wix needed a comprehensive monitoring solution to keep pace with their rapid development cycle. With over 60 daily deployments and a complex DevOps environment, Wix required real-time visibility and anomaly detection. Solution: Wix adopted Anodot's machine learning-powered monitoring platform. Anodot analyzes data across various tools, including server logs, APM solutions, and application frameworks. This holistic view allows Wix to identify potential issues before they impact users. Benefits: Proactive monitoring: Anodot uses machine learning to detect anomalies and predict potential problems. Reduced workload: Anodot automates many tasks, freeing up DevOps engineers to focus on higher-level activities. Improved collaboration: Anodot integrates with Slack and Git, streamlining communication between developers and operations teams. Faster issue resolution: Real-time anomaly detection allows for faster identification and resolution of potential problems. Key Takeaway: Wix's experience demonstrates how machine learning can revolutionize DevOps monitoring. By providing a central platform for all metrics and enabling proactive anomaly detection, Anodot empowers DevOps teams to achieve a higher level of efficiency and reliability. Changes made: Removed unnecessary keyword stuffing: Removed phrases like "full monitoring and visibility with Anodot" and replaced them with more natural descriptions. Focused on user value: Highlighted the benefits Wix achieved with Anodot, such as proactive monitoring and faster issue resolution. Replaced promotional language: Avoided phrases like "turnkey platform" and "preemptively makes diagnoses" that could be perceived as biased. Improved flow: Streamlined the structure and rephrased some sentences for better readability.

The ELK stack (ElasticSearch, Logstash, Kibana), by Elastic, has gained tremendous popularity in the last several years. By viewing Kibana graphs derived from the event and log data stored in Elastic, analysts, developers and DevOps can visually get actionable insights in real time. But what happens when you start to have too many graphs to track? For example, looking at page views and conversion rates from all your users,  grouped by country, user device type and OS would generate thousands of combinations leading to thousands of graphs. Can you really track and gain insights when the number of interesting graphs increases to thousands and hundred of thousands (and millions in some cases)? The answer is quite clear - No, this approach doesn’t scale. Unless you can afford hiring an army of experts to look at them. Data Science to the rescue... This is where data science in general, and specifically Anodot’s anomaly detection service, scales your monitoring capabilities, without needing to hire that army. Let the machine track the thousands to millions of graphs (aka metrics) for you, automatically learn their normal behavior and how they are related, and alert you when one or more change their pattern and behave abnormally. Integrating Anodot with ELK in three steps (These instructions assume that you already have a running ELK stack, and have an active Anodot account - if you don't, contact: [email protected] or fill out this form) Follow this great post by Erik Redding and/or this one.  to see how you can send metrics using Graphite protocol with logstash. Install the Anodot-Relay which supports the graphite protocol. Add the Anodot relay to your logstash configuration output section as graphite output, set  the host parameter as the relay address. output { elasticsearch { host => localhost }    graphite {    host => ANODOT_RELAY_IP    ….    } } That’s all you need to do, and you can start sending metrics to Anodot for immediate analysis. By adding Anodot as a layer on top of your kibana, you will be alerted to any anomaly, which will dramatically decrease your detection and investigation time. Enjoy.

Anodot's Uri Maoz explains how real-time anomaly detection can save your company millions of dollars, and what you should look for in this type of monitoring system for both your technical and your business metrics.

At Anodot, our solution analyzes the massive amount of metrics collected by data-centric businesses. These metrics originate from multiple sources, such as business processes, applications, systems, networks, and anything in between. One important use case for the Anodot technology is the rapid detection of IT environment issues so that they can be fixed quickly. Our method for detection is to find anomalous behavior in the metrics. This type of behavior usually indicates an existing or impending problem. Anodot for Anodot A week before we released our alpha version to our first customers last October, we decided to let Anodot work on itself, that is, to detect its own anomalies. We started monitoring our systems and application components in order to generate our own business metrics. One of our important business metrics is the number of anomalies we can detect per minute. For example an application metric is the average latency of a process running within our application. We started collecting large amounts of these metrics with the understanding that they would be important for keeping Anodot up and running. Fast Self-Analysis The decision to test our own system quickly yielded results. Just hours after the automatic self-analysis process commenced, our system found a strange anomaly: This anomaly lasted for 30 minutes and then stopped. In the anomaly, the latency of one of our processes went up dramatically for 0.1% of the times that the process ran, a few thousand times per minute. During the 0.1% of these occurrences, the latency rose from about a second to over 60 seconds! This meant that every once in a while, at unpredictable times, the process would take over 60 seconds to run. If this issue were to occur at the same time that multiple Anodot users were attempting to view their systems, they could experience a lengthy delay (see charts below). Counting on Anodot Rather than on Luck The problem turned out to be a bug in our code, an unanticipated lock/sync problem. Understanding and fixing the bug was not difficult – however, we would not have been able to detect such intermittent problems with standard monitoring tools. The fact that we were using our own tools reinforced the market need for automatic anomaly detection.  Without Anodot, we would have relied only on chance. By depending on manual monitoring, we would have needed to be lucky enough to look at the graphic metrics correctly, at exactly the time when the problem occurred. If we had missed this problem, we would have discovered it only if our users would have contacted us to complain about an intermittent latency problem. Self-healing System? Is this the first step towards an intelligent system that can heal itself?  Perhaps. It certainly is evidence of an intelligent system, one that can detect its own bugs automatically, without requiring programmers to define how to look for the bugs. It is also a step in defining the essence of machine learning:  Our algorithms don't just power our system – they help fix it as well! Most importantly, by running Anodot on Anodot, we are able to provide a better, smoother experience to our customers.