Corey Gilmore, Director of Data and Analytics at PMC, a large publishing company, presents how they identify anomalies in their Google Analytics using Anodot.

Most organizations monitor and report the overall availability of their site or service. Here is an example of how Facebook reports the status of their API availability on their developers’ site. This error rate represents 99.978% availability, which is fantastic! But what if it means that this is a result of one of the following scenarios: 100% failure on android Jelly Bean 4.2.x 25% failure for a new promising startup that is integrating with Facebook’s authentication services Facebook’s DAU (Daily Active Users) hit 1.18 billion according to their last earning report (Q3 2016); if we assume that each user represents only 1 API call per day, that means  259,600 API calls fail daily. And that means 259,600 users experience failed interactions. How can we find the common dominator for those interactions to find the root cause and fix it?  Which API has the most errors? In which region? On which browser? When we average things out, we lose visibility of the underlying root cause that impacts the metric we are measuring, be it availability, transaction volume or conversion rate. It’s like the statistician’s joke: “Then there was the man who drowned while crossing a stream that was, on average, six inches deep.” Most organizations look at the big picture and act only when there is a significant change to one of the key metrics. But the fact of the matter is that the business impact of many small events over time (figure 1) can be the same or worse than one short major incident (figure 2).   Average Monthly Availability: 99.85% Impact Start: 0:14 Restore: 0:50 TTR: 36 minutes Average Hourly Availability: 59.5% Average Daily Availability: 98.22% Average Monthly Availability: 99.85% There are few constraints that drive organizations to take a high level look at metrics: Technology: Until recently, technology didn’t support the level of granularity required to monitor the health of individual transactions. Dashboards can’t scale for more than a few dozen signals and setting up alerts at a granular level (e.g. customer, partner, city) was not supported due to performance and scalability challenges. Human brain: Even if we could provide multiple dashboards with hundreds of different signals, the human brain is not equipped to process all of them and definitely not equipped to correlate the different signals to find the root cause of an issue. When a popular ride sharing startup was in its earliest stages, a critical partner integration would break occasionally and go unnoticed for hours.  Once the problem was detected, the startup’s dev ops would have to call the account manager at the partner company to have the issue fixed. The partner, with millions of merchant integrations, simply could not monitor the health of each integration, therefore compromising by looking at enterprise level KPIs (maturity level 1 for detection and 5 for collection). Four years later, the ride sharing startup became one of the partner largest customers with a huge volume of traffic. The startup didn’t stop working with the partner mainly due to personal relationship - but what if they had? How many other customers didn’t have the same personal relationship with the partner company and moved their business somewhere else? The only way to solve this issue and get insights on a granular level is by embracing new machine learning and anomaly detection technologies that can process huge amounts of data in real time and surface anomalies on an indefinite number of dimensions. This enables the shift to a new paradigm, BI 2.0, in which machine learning is used to gain deeper insights into business metrics and automated correlation enables faster root cause analysis. If this sounds familiar, you should consider implementing an anomaly detection solution to see how many insights are hidden in your data. I know that you might think that you need to hire data scientists to implement such a solution but the reality is that it is much easier than you might think. Take advantage of advanced anomaly detection products that automates the entire process.  All you need to do is push your metrics and uncover the hidden insights.

Greg Pendler of Netseer presents how his Adtech company is using Anodot to identify anomalies in real time, to keep their business working efficiently.

In today's competitive market, digital businesses such as fintech, ad tech, media and others are always on the lookout for the next big thing to help streamline their business processes. These businesses are constantly generating new data and often have systems and people in place to monitor what is going on. For example, within one company, you might find an IT group monitoring network performance while someone in product management watching page response time and user experience while marketing analysts track conversions per campaign and other KPIs. It is no secret that anomalies in one area often affect performance in other areas, but it is difficult for the association to be made if all the departments are operating independently of one another. In addition, most of the available tools for this type of monitoring look at what has happened in the past, so there is a built-in delay between when something important happens, and when it may (or may not) be discovered via the monitoring process. Each business incident discovered could be an opportunity to save money, plug a leaky funnel, or to potentially create new business opportunities. In an ideal setting, a large-scale business incident detection system would take a holistic approach to anomaly detection, and do it in real time. Monitoring and analyzing these data patterns in real-time can help detect subtle – and sometimes not-so-subtle – and unexpected changes whose root causes warrant investigation. The graph below illustrates an e-commerce company that sees an unexpected increase in the number of gift cards purchased online while simultaneously experiencing a drop in the revenue expected for the gift cards. By correlating the two anomalies, we understand that there has been a price glitch that could cost the company a lot of money if not caught and addressed quickly. [caption id="attachment_2402" align="aligncenter" width="1320"] Price glitch that could cost ecommerce a lot of money[/caption] As a business grows, more and more incidents can go undetected unless an anomaly detection system is directed to make sense of the massive volume of metrics. Not every metric is directly tied to money—but most metrics are tied to revenue in some way. Today, most companies employ manual detection of anomalous incidents by creating a lot of dashboards and monitoring daily or weekly reports or by setting upper and lower alert thresholds for each metric. These methods leave a lot of room for human error and false positives or missed anomalies. To find out how to leverage automated anomaly detection, where computers look at this data and sift through it automatically and quickly, to highlight abnormal behavior and alert on it, check out our White Paper: Building a Large Scale, Machine Learning-Based Anomaly Detection System, Part 1: Design Principles.      

Josh Bycer from Game Wisdom sat down with Anodot's Ira Cohen and Rebecca Herson to discuss how things are changing with the mobile market, and the work Anodot is doing in the field of analytics.

The first in our 3-part guide to anomaly detection covers the components necessary to designing a machine learning-based anomaly detection system.

Just as our company is committed to providing an innovative real-time business incident detection solution for our customers, we are also committed to giving back to our community. We are pleased to announce our recent partnership with Tmura, a foundation established by leading Israeli venture capital funds to involve the high-tech sector in supporting charitable activities. Innovative, early-stage companies with potential for growth donate options to the Tmura Foundation, which are convertible (at exit) into equity. When the company has an exit, Tmura sells its shares and donates the proceeds to various education and youth-related charities in Israel. We are proud to join Tmura's more than 470 donor companies including Waze, Wix, M-Systems (now SanDisk), CyberArk and eXelate, who have already contributed more than $13.9 million to help various organizations throughout the country. Some of the organizations who have received funding from Tmura include: Big Brothers Big Sisters of Israel - affiliated with the international Big Brothers umbrella Chinuch L’Psagot - enrichment program focusing on students with potential to excel HaGal Sheli - working with at-risk youth, using surfing as an educational tool HiddenSparks - develops and supports professional development programs to help increase understanding and support for teaching to diverse learners Machshava Tova - computer centers in peripheral areas to “narrow the digital gap” MEET - educational excellence program, empowering Israeli and Palestinian young leaders Tasa/Olim Beyahad - internship program for exceptional Ethiopian Israeli university students We are happy to have this opportunity to make a difference in our community.

NetSeer provides market leading visual monetization solutions for advertisers and publishers backed by its patented ConceptGraph™ intent engine. The company's InImage advertising solution is changing the game in the industry as it delivers exceptional performance across desktop, mobile, and video inventory. As a leading adtech company, Netseer sees a large portion of internet traffic and uses its algorithms to analyze the content, bringing these together to provide publishers with targeted ads, and bidding on advertising exchanges. Before finding Anodot, they tried several tools such as Graphite and alerting systems to track the company’s business and operational KPIs, yet they still were not alerted accurately or in a timely manner on key business problems they were facing. And then they found Anodot. With Anodot, NetSeer easily pulled in their Graphite data and immediately benefited when we highlighted issues by detecting anomalies in the streaming data. Previously, NetSeer only received singular elements of detection and reporting and the team spent time patching everything together to get the information they needed. Soon, more and more departments will be able to benefit from Anodot insights. “We’re adopting Anodot throughout practically the whole company. We started with monitoring our infrastructure, and then quickly saw the benefit to tracking key product and campaign KPIs. I can’t imagine a day going by without our teams checking how we are doing on Anodot,” said Amir Bakhshaie, Head of Product at NetSeer. Click here to read the summary (with a link to download the full case study) and find out how with Anodot, one solution works together, integrated with Graphite to provide this ad tech company complete business incident detection and notification.  

Delayed business insights cost companies millions of dollars. Data-centric companies like Web-based businesses, AdTech, FinTech and IoT face unique challenges because it is impossible to manually track the millions of metrics that are generated in today's digital businesses. Static thresholds for seasonal data are either meaningless or cause alert-storms. So...what can we do? This was the discussion topic of Anodot’s first Meetup last week at the Google Headquarters in Mountain View, CA. The crowd started arriving early eager to mingle with a pizza slice in hand. Networking had officially started! The atmosphere was lively, voices echoed throughout the room. The entire Anodot US team was present and ready to socialize. The second part of the evening was slowly approaching and the 150 Google chairs started filling up. Folks came to learn how to avoid business insight latency, and thus save $$, and we were anxious to provide the answers. First up was Anodot’s own Uri Maoz, VP of US Business. “What is real-time business incident detection?” he asked. The crowd went wild! No...not yet. But they did enjoy Uri’s unique sense of humor and the discussion around how predictive anomaly detection can identify revenue-impacting business incidents in minutes(!) not days or weeks. Uri explored the benefits and challenges of implementing Anomaly Detection, and also shared industry benchmarks and customer case studies. Questions poured in at the end. Click here for the full Facebook Live video of Uri's presentation. Next up was Corey Gilmore, PMC Chief Architect. He shared details about PMC challenges with gaining real time insights from Google Analytics (using current BI tools) and how these challenges can be overcome with Anomaly Detection. Click here for the full video of Corey's presentation. Last but not least, Greg Pendler, Sr. Director of Technical Operations at Netseer, took the stage. Greg discussed the implementation of Anomaly Detection in AdTech. Specifically, he unveiled the contribution of Anomaly Detection in analysis of business and technical data across multiple teams and how Anomaly Detection saved the company money! Click here for the full video of Greg's presentation. Anodot’s Founder and Chief Data Scientist, Ira Cohen, was also present. He reflected on two remarks from Greg's presentation that resonated with him: Trust in the anomalies. and Business (data) is where anomalies shine. Additionally, three lucky winners walked out with amazing $150+ prizes and a smile on their face. Actually, everyone left happy. One attendee thanked us for organizing an educational event. Another attendee wrote on the Meetup page: “Made very simple to understand, got a good return of time invested.” Score! We’d like to thank all who attended and contributed to this important discussion, our speakers who shared insights, the Google team for hosting us and @TeamAnodot for executing our first Meetup successfully! We look forward to hosting many, many more. Cheers!