<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Neil Boyette on Medium]]></title>
        <description><![CDATA[Stories by Neil Boyette on Medium]]></description>
        <link>https://medium.com/@neil.boyette?source=rss-f9879f7ff7ca------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*RjgC9edllc3WEZiJZYGn8w.jpeg</url>
            <title>Stories by Neil Boyette on Medium</title>
            <link>https://medium.com/@neil.boyette?source=rss-f9879f7ff7ca------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 16:35:45 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@neil.boyette/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Support for a Greater Quantity of Standing Alerts with IBM Cloud Pak for AIOps 4.5.0]]></title>
            <link>https://medium.com/ibm-watson-aiops/support-for-a-greater-quantity-of-standing-alerts-with-ibm-cloud-pak-for-aiops-4-5-0-06956baf1b1d?source=rss-f9879f7ff7ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/06956baf1b1d</guid>
            <category><![CDATA[aiops]]></category>
            <category><![CDATA[alerts]]></category>
            <category><![CDATA[scale]]></category>
            <dc:creator><![CDATA[Neil Boyette]]></dc:creator>
            <pubDate>Wed, 03 Apr 2024 14:39:39 GMT</pubDate>
            <atom:updated>2024-04-03T14:39:39.806Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*S0-1bqd4z7taQkEnfKKo_g.png" /></figure><p>A lot of the focus with an AIOps platform is on the number of events it can ingest and stream through. However, a big consideration should also be placed on the number of active alerts (also referred to as the standing count) that the platform can handle. An enterprise AIOps platform such as IBM Cloud Pak for AIOps supports clients that process from tens to hundreds of millions of events per day. Even when achieving 99% noise reduction through event de-duplication, suppression, several types of correlation, and prioritization algorithms, this still can leave a substantial number of active alerts.</p><p>By supporting 200,000 active alerts, IBM Cloud Pak for AIOps now equals or exceeds the standing count in IBM Netcool, OMNIbus ObjectServer, and IBM Netcool Operations Insights while supporting many more analytics operations.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*5WXH-9VF5x6-FUl4mIj6BQ.png" /></figure><p>There are 3 areas to consider when looking at the supported active alerts:</p><p>1. How is the ingestion of additional events impacted by the standing alerts?</p><p>2. How are the analytics being performed impacted by the standing alerts?</p><p>3. How are the active alerts shown to a user?</p><h3>How is the ingestion of additional events impacted by the standing alerts?</h3><p>A straightforward concern is whether there is any performance impact in ingesting events into an IBM Cloud Pak for AIOps deployment depending on the amount of alerts contained therein. In short, the answer is that it does not. The time spent ingesting events stays constant, regardless of the amount of standing alerts, supporting a steady rate of 700 events per second, with bursts up to 1,000 events per second (for details on the assumptions made, see the <a href="https://www.ibm.com/docs/en/cloud-paks/cloud-pak-aiops/4.5.0?topic=planning-hardware-requirements">Hardware requirements</a> for IBM Cloud Pak for AIOps). In other words, IBM Cloud Pak for AIOps can support over 60M events per day, regardless of the number of standing alerts.</p><h3>How is any analytics being performed impacted by the standing alerts?</h3><p>The reason for having active alerts is not only to display them, but also for analytics to reference them. For example, with de-duplication, an incoming event is first matched to existing active alerts and added to them when they match. With alert correlation, a given alert is potentially correlated with any of the active alerts. IBM Cloud Pak for AIOps has been engineered in a way that these analytics operations are applied consistently and in near real-time even with large active alert counts.</p><h3>How are the active alerts shown to a user?</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/360/1*xF-0T77HoOGq4S2h3KKgoA.png" /></figure><p>The third consideration is displaying the alerts to users. Users view alerts in many different ways, with custom filters, search queries, custom attributes, and customized sets of columns in an alert list view. This is a lot more efficient than looking at a single list with 200,000 rows. As such, IBM Cloud Pak for AIOps supports a configurable limit for the number of alerts to be displayed. This limit supports the ability to filter, to search, and to customize the set of attributes and columns displayed. To give a tradeoff between cluster load and the number alerts, limit can be set to up to 10,000 alerts.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*AGu7MFgzM7brtHbDauX6Lw.png" /></figure><p>To ensure users never miss an alert, the number of alerts for the given custom filters and search queries are always clearly shown. This way a user can always filter further if they have too many alerts to easily handle.</p><h3>Conclusion</h3><p>IBM Cloud Pak for AIOps 4.5.0 supports a standing alert count of 200,000 alerts. This support is across its end-to-end workflow, from data ingestion, analytics, and display. This is just a first step as we are continuously working to further grow the scale for IBM Cloud Pak for AIOps.</p><p>Learn more about Cloud Pak for AIOps at <a href="https://www.ibm.com/products/cloud-pak-for-aiops">https://www.ibm.com/products/cloud-pak-for-aiops</a></p><p>A special thanks to Chris Appleton, Matas Bartosevicius, Cormac Cummins, Mary-Jo Linehan-McGuinness, and Joshua Suckling.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=06956baf1b1d" width="1" height="1" alt=""><hr><p><a href="https://medium.com/ibm-watson-aiops/support-for-a-greater-quantity-of-standing-alerts-with-ibm-cloud-pak-for-aiops-4-5-0-06956baf1b1d">Support for a Greater Quantity of Standing Alerts with IBM Cloud Pak for AIOps 4.5.0</a> was originally published in <a href="https://medium.com/ibm-watson-aiops">IBM IT Automation and AI</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[New Backup and Restore Capabilities with IBM Cloud Pak for AIOps 4.5.0]]></title>
            <link>https://medium.com/ibm-watson-aiops/new-backup-and-restore-capabilities-with-ibm-cloud-pak-for-aiops-4-5-0-53100b0ac65d?source=rss-f9879f7ff7ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/53100b0ac65d</guid>
            <category><![CDATA[backup]]></category>
            <category><![CDATA[geo-redundancy]]></category>
            <category><![CDATA[aiops]]></category>
            <dc:creator><![CDATA[Neil Boyette]]></dc:creator>
            <pubDate>Tue, 02 Apr 2024 13:43:41 GMT</pubDate>
            <atom:updated>2024-04-04T14:49:29.257Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*oqhhjl-hTQC4Et6NvvD8lg.jpeg" /></figure><p><strong>Authors: Neil Boyette &amp; Viraj Vyas</strong></p><h3>The need for Backup and Restore with IBM Cloud Pak for AIOps</h3><p>Backup and restore refers to technologies and practices for making periodic copies of data and applications to a separate, secondary device and then using those copies to recover the data and applications, and the business operations on which they depend (ref: <a href="https://www.ibm.com/topics/backup-and-restore">https://www.ibm.com/topics/backup-and-restore</a>).</p><p>Having a recent backup available is key to minimizing disruptions in case of a disaster where the Red Hat OpenShift cluster is not available for any reason, including natural disasters, but also if you introduce a logical error into the disk storage, encounter ransomware, etc.</p><p>With IBM Cloud Pak for AIOps 4.5.0, we have partnered with IBM Storage Fusion to provide an option for backup and restore that is easier to use, faster, and less disruptive, so that service can be restored quickly on the same cluster, or another one in a different geography. Geo-redundancy is supported by having backups stored in a geographically dispersed manner and with the ability to restore a cluster in another geography.</p><h3>What was previously available?</h3><p>IBM Cloud Pak for AIOps 4.4.1 and earlier can be backed up and restored using technology like OpenShift APIs for Data Protection (OADP) and Velero (ref: <a href="https://www.ibm.com/docs/en/cloud-paks/cloud-pak-aiops/4.4.1?topic=pak-backing-up-restoring-cloud-aiops">https://www.ibm.com/docs/en/cloud-paks/cloud-pak-aiops/4.4.1?topic=pak-backing-up-restoring-cloud-aiops</a>). These manual steps allow for full backups to be made which can be restored to a different cluster. However, this can incur some service interruptions as workloads have to be temporarily stopped while backups are created.</p><h3>Why IBM Storage Fusion?</h3><p>IBM Storage Fusion enhances IBM Cloud Paks with tightly integrated enterprise ready data services including backup, restore and disaster recovery capabilities for Cloud Pak environments . Using automated policy-based recipes with application consistent backup and recovery, IBM Storage Fusion provides the best Recovery Time Objective and Recovery Point Objective (RTO/RPO) for cloud-native applications. (ref: <a href="https://www.ibm.com/products/storage-fusion">https://www.ibm.com/products/storage-fusion</a>).</p><p>The IBM Storage Fusion backup and restore service works with all CSI compatible storage types for example, Portworx, ODF and Ceph in addition to the IBM Storage Fusion appliance and the included IBM Storage Fusion Essentials entitlements. Fusion stores backups on S3 compatible Object Storage thus providing flexibility in storage options.</p><p>By using IBM Storage Fusion’s backup and restore capabilities, you can automate the existing manual backup and restore steps mentioned above. IBM Storage Fusion also provides an easy to use UI to schedule and manage backups.</p><p>However, the biggest advantage to using IBM Storage Fusion for backing up IBM Cloud Pak for AIOps is that it is done without user interruption. In other words, it provides an online backup. Without the need for maintenance windows, backups can be performed more frequently thus lowering the Recovery Point Objective (RPO) significantly. Our recipes also provide for incremental backups thus lowering the time it takes to perform the backup while also lowering storage costs.</p><h3>Deployment Architecture</h3><p>By using IBM Storage Fusion’s Hub and Spoke architecture, you can restore IBM Cloud Pak for AIOps on another cluster with minimal effort.</p><figure><img alt="Spoke and Hub setup of Fusion." src="https://cdn-images-1.medium.com/max/1024/1*aSktUcQu4ui-Jtoo_FmG8w.png" /></figure><p><em>Diagram of Scenario 1: Spoke and Hub setup of Fusion.</em></p><p>The diagram above shows how IBM Storage Fusion can be set up alongside Cloud Pak for AIOps by taking advantage of its Hub and Spoke architecture. The diagram shows two clusters, Cluster P (primary) on left and Cluster B (backup) on right.</p><p>On Cluster P, IBM Cloud Pak for AIOps is running and IBM Storage Fusion is installed and configured alongside it on the same cluster. IBM Storage Fusion on Cluster P is running in hub mode and configured in a way that it takes regular backups to Object Storage, displayed at the bottom.</p><p>On cluster B, only IBM Storage Fusion is running in spoke mode and it is connected to the same Object Storage using Fusion Hub (on cluster P). Once this configuration is completed (ref: <a href="https://www.ibm.com/docs/en/storage-fusion-software/2.7.x?topic=restore-hub-spoke-model-overview">https://www.ibm.com/docs/en/storage-fusion-software/2.7.x?topic=restore-hub-spoke-model-overview</a> ), you can restore IBM Cloud Pak for AIOps to cluster B using a few simple steps in the IBM Storage Fusion GUI.</p><h3>Summary</h3><p>In conclusion, with IBM Storage Fusion assisted backup and restore, IBM Cloud Pak for AIOps 4.5.0 now supports online backups, performs backups faster due to taking incremental snapshots, uses less storage, and is a lot easier to manage.</p><p>Learn more about Cloud Pak for AIOps at <a href="https://www.ibm.com/products/cloud-pak-for-aiops">https://www.ibm.com/products/cloud-pak-for-aiops</a></p><p>Learn more about IBM Storage Fusion Backup at <a href="https://ibm.github.io/storage-fusion/backup/overview">https://ibm.github.io/storage-fusion/backup/overview</a></p><p>Special thanks to Jim Smith, Sandeep Prajapati, John Keane, Nick Banyard, Chris Appleton and Mike Moroney</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=53100b0ac65d" width="1" height="1" alt=""><hr><p><a href="https://medium.com/ibm-watson-aiops/new-backup-and-restore-capabilities-with-ibm-cloud-pak-for-aiops-4-5-0-53100b0ac65d">New Backup and Restore Capabilities with IBM Cloud Pak for AIOps 4.5.0</a> was originally published in <a href="https://medium.com/ibm-watson-aiops">IBM IT Automation and AI</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Leverage Anomaly Detection without worrying about noise]]></title>
            <link>https://medium.com/ibm-cloud/leverage-anomaly-detection-without-worrying-about-noise-a27f5b037d3d?source=rss-f9879f7ff7ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/a27f5b037d3d</guid>
            <category><![CDATA[noise-reduction]]></category>
            <category><![CDATA[anomaly-detection]]></category>
            <category><![CDATA[false-positive]]></category>
            <category><![CDATA[aiops]]></category>
            <dc:creator><![CDATA[Neil Boyette]]></dc:creator>
            <pubDate>Wed, 27 Jul 2022 08:51:02 GMT</pubDate>
            <atom:updated>2022-07-27T08:53:07.938Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>By Neil Boyette &amp; Ian Manning</strong></p><p><em>Anomaly Detection has been around for a long time. But what is an Anomaly? More importantly, how can you adopt Anomaly Detection in your business and why can’t we just get rid of false anomalies?</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/700/1*REyu6gwqyUVjCbUHPryYKA.jpeg" /></figure><p>Anomaly Detection is the process of learning the normal pattern of behavior (using AI) and then indicating when it has changed significantly, or something unexpected has occurred. The indication is a called an “anomaly” but really it is just an Event that tells you about a significant change or abnormal behavior that has occurred.</p><p>An Anomaly can be an early indication of an emerging problem, but it can also indicate a condition that is simply different than what has been previously observed. For example: a server is using more memory than normal. This may not be problematic, but the question is: <em>why is it using more memory than normal?</em></p><p>Using many sophisticated approaches, and based on thousands of data points, Anomaly Detection will know when a problem has not been seen before. In IBM Cloud Pak for Watson AIOps, we currently have two types of data on which we do Anomaly Detection: Logs and Metrics. The platform automatically combines 7 different algorithms for metric anomalies and several for log anomaly to be confident in the anomalies it finds. It could be that the server has been re-purposed and that is expected behavior — the new normal. However, It could also be that someone is mining BitCoin on it, or there is a memory leak — and both possibilities are worth investigating. As such, a valid anomaly is simply a confirmed deviation from what is expected.</p><p>Valid anomalies–like high memory usage–are often dismissed as false positives. False positives occur when the algorithm creates a notification about a change that doesn’t necessarily warrant attention — it is not interesting, or not significant enough to prompt action. This is a key point, as a valid anomaly can still be not interesting and thus be easily considered as noise. Too many false positives in this sense and anomaly detection becomes useless since. As such, IBM Cloud Pak for Watson AIOps separates out detecting anomalies and noise reduction, so that the SRE gets <strong>the right information at the right time</strong>.</p><p>In IBM Cloud Pak for Watson AIOps, you have the ability to analyze all your logs and metrics using anomaly detection. But you also have control over the conditions in which you want to get notified. Anomalies and other events are first de-duplicated. This way, you don’t have the constant drone of, for example, a warning that “memory has been found to be abnormally high”, then 5 secs later again — it is still high, then 5 sec later again, etc. Instead, such notifications are combined into a single alert. These alerts undergo a further series of noise reduction algorithms: from different ways of correlating (grouping using co-occurrence, topology, scope etc.), augmenting them with topology and automatons (which could auto-resolve the alert), to, finally, a set of policies indicating importance.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*yQ2a2fs9bDNjHD_Df6-Bjg.png" /><figcaption>IBM Cloud Pak for Watson AIOps Capabilities</figcaption></figure><p>The end result is that each (anomaly) event, can have several different outcomes:</p><ul><li>The event can be combined with previous occurrences during de-duplication. Here, the alert is updated with the fact that the event is still occurring through, for example, a count or a last occurrence time-stamp.</li><li>The event is associated with an alert, which in turn is available for introspection, but isn’t deemed important enough to automate or interrupt the SRE.</li><li>The event is associated with an alert that in turn does have automations associated with it. This can auto-resolve the problem or–depending on where the client is on the adoption curve–can be manually approved and executed.</li><li>The event is associated with an alert that in turn isn’t important enough to spawn its own story; however, is related to one, as context. This allows the SRE to quickly understand the context without interrupting them.</li><li>The event is associated with an alert that in turn is important enough to spawn its own story; as such it is augmented with many different contexts and insights, allowing an SRE to understand and take action right away.</li></ul><p>This range of outcomes allows each SRE to customize the behavior to suit their needs. Circling back to the abnormal memory usage example; IBM Cloud Pak for Watson AIOps would treat the single anomaly in many different ways, depending on whether there is a (related) problem occurring, whether it is part of an important application, whether the anomaly was already reported, etc. In short, looking at anomalies in context with other Alerts, Topology, and other useful information allows you to be notified on business critical Alerts, and yet see the full context which will help you reduce Mean Time to Know (MTTK) and help you solve the issue quickly.</p><p><a href="https://www.ibm.com/cloud/cloud-pak-for-watson-aiops">Learn more</a> about IBM Cloud Pak for Watson AIOps.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=a27f5b037d3d" width="1" height="1" alt=""><hr><p><a href="https://medium.com/ibm-cloud/leverage-anomaly-detection-without-worrying-about-noise-a27f5b037d3d">Leverage Anomaly Detection without worrying about noise</a> was originally published in <a href="https://medium.com/ibm-cloud">IBM Cloud</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Why AIOps is better than hiring a data scientist]]></title>
            <link>https://medium.com/ibm-cloud/why-aiops-is-better-than-hiring-a-data-scientist-434129522962?source=rss-f9879f7ff7ca------2</link>
            <guid isPermaLink="false">https://medium.com/p/434129522962</guid>
            <category><![CDATA[watson]]></category>
            <category><![CDATA[sre]]></category>
            <category><![CDATA[automation]]></category>
            <category><![CDATA[aiops]]></category>
            <category><![CDATA[data-scientist]]></category>
            <dc:creator><![CDATA[Neil Boyette]]></dc:creator>
            <pubDate>Tue, 29 Jun 2021 06:19:18 GMT</pubDate>
            <atom:updated>2021-06-29T06:46:45.910Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>By Neil Boyette &amp; Isabell Sippli</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mduEbZDAoF-9cASIHGg_sA.jpeg" /></figure><p>The first thing many people do when approaching the AIOps trend, is to look for a definition of AIOps. Gartner has published <a href="https://www.gartner.com/en/information-technology/glossary/aiops-artificial-intelligence-operations">one of the most popular definitions</a>:</p><p><em>AIOps combines big data and machine learning to automate IT operations processes, including event correlation, anomaly detection and causality determination.</em></p><p>On seeing this definition, one might think: big data and machine learning … ok, I shall hire a couple of data scientists and let them work with my operations data. Maybe they can help me reduce service tickets, get better insights into my incidents, and maybe even apply some predictions to avoid outages?</p><p>Sounds simple? Actually, it is not.</p><p>Let’s explore a couple of reasons why doing AIOps correctly is not so simple when you need to start from scratch:</p><p><strong>1. Applying ML to IT data — but what data?</strong></p><p>“Volume, variety and velocity” are the defining dimensions of data. But while you might be able to deal with volume, it gets trickier when it comes to handling variety and velocity. IT (operations) data is highly diverse, and almost always includes logs, metrics, events, and tickets. If you’re very lucky, each data type is coming from a single source, e.g. all log data is collected in a single place, or all event data is normalized in a system like <a href="https://www.google.com/url?sa=t&amp;rct=j&amp;q=&amp;esrc=s&amp;source=web&amp;cd=&amp;cad=rja&amp;uact=8&amp;ved=2ahUKEwi7p_eql7zxAhWCilwKHdyiDzcQFjAAegQIAxAD&amp;url=https%3A%2F%2Fwww.ibm.com%2Fdocs%2Fen%2Fnetcoolomnibus%2F8.1%3Ftopic%3Doverview-introduction-tivoli-netcoolomnibus&amp;usg=AOvVaw14RYFUIUMFYsV8eiteq7AU">Netcool OMNIbus</a>. However, we rarely see this when working with large clients. Most often, data is spread over several silos, and includes structured and unstructured data. Besides the heterogeneity, IT data often occurs in large volumes. For example, we frequently work with clients dealing with terabytes of logs each day, combined with double digit millions of events.</p><p><strong>2. Applying ML to IT data — but what ML?</strong></p><p>Finding the right algorithms, which perform at scale, is hard. Before you hit upon the right algorithm, you have to identify what you are actually looking for. Are you trying to find anomalies in your logs? If so, what anomalies? Are you trying to find correlations for your events? If so, what correlations? What makes your system believe a correlation is useful and meaningful (a true positive)? Once you have found the right algorithm, you have to code the model, customize it to your data, train and tune it.</p><p><strong>3. Applying ML to IT data — but what environment?</strong></p><p>The majority of enterprises operate across a mixed set of environments; cloud native (on Kubernetes or OpenShift), traditional on VMs or Bare Metals, mission critical application on Z. An added challenge is that these are spread across multiple data centers and clouds. Bringing all this information together is complicated, and validating that a given algorithm applies to specific data and runtimes is time-consuming.</p><p><strong>4. Even if you overcome the above challenges — how do you present your findings?</strong></p><p>IT Ops is all about speed, as every second counts in case of an outage. Creating regular reports might help you historically, but you also want to present your insights to your team in charge — be it a traditional IT Operations team or your SREs.</p><p>Luckily, IBM is helping to solve these problems. With <a href="https://www.ibm.com/cloud/cloud-pak-for-watson-aiops">Cloud Pak for Watson AIOps</a>, we’re addressing those challenges, and more. Here’s how:</p><p>1. Cloud Pak for Watson AIOps comes with a large amount of out-of-the-box connectors, which normalize your heterogeneous data into a single store. It provides over 170 adapters &amp; connectors to the most common IT systems worldwide. For those connectors, we have analyzed the data source, identified which is the best information to be pulled, and mapped it to our common format.</p><p>2. Cloud Pak for Watson AIOps builds on more than 100 patents. We are a team of world class data scientists and ML engineers, that have identified the right algorithms and approaches per data type. This group is backed by groups of researchers in IBM Research who are always looking to the future, to see what innovations can be applied to AIOps.</p><p><strong>Event correlation</strong></p><p>We are combining 3 approaches for you:</p><p>(i) Through a modified version of FPGrowth (<a href="https://dl.acm.org/doi/10.1145/335191.335372">Frequent Pattern Mining</a>) that we apply to historic event data, we are finding sets of events that tend to co-occur. This algorithm trains automatically on your historic data</p><p>(ii) Through our application management component, we can find events that are proximate on nodes in the topology. If you want us to, we can use that proximity as a correlation approach</p><p>(iii) Searching for similar values of event fields. You can configure which values to look for, and where, and we add that to our correlation.</p><p>Eventually, we can show how all approaches inter-relate, as you can see in:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*O5LO02U3VumWqabV7_5KPg.png" /><figcaption>Event Correlation Sample</figcaption></figure><p><strong>Log Anomaly detection</strong></p><p>We apply various types of NLP to create groups of templates. The templates in turn are used to extract features from the log message’s text. These features in turn are augmented by specific entities extracted from the log message’s text such as for error codes and by <a href="https://www.ibm.com/cloud/blog/using-language-models-to-optimize-it-operations-management-in-watson-aiops">features extracted using Language Models</a>. This combined set of features is then used to train a set of models for each of the components being monitored.</p><p><strong>Metric Anomaly detection</strong></p><p>We receive and analyze metric data from a range of sources, and then apply a set of time-series algorithms like Robust Bounds, Variant/Invariant, Finite Domain and Predominant Range to capture seasonality, significant trends and to perform forecasting. (see article <a href="https://medium.com/@rama.akkiraju/watson-aiops-ai-for-it-operations-management-c6565906c3e8">here</a>).</p><p>For all of the above, we have tested our algorithms at scale, and on typical, industry-specific data sets.</p><p>Additionally, explainability is at the forefront of our work. This is critical as without good explainability, there isn’t a clear way to establish trust with your IT Operations team, or your SREs.</p><p>In the image below, you can see how we present historic evidence to explain how we have identified that the two depicted events co-occur together. Each purple bar in the timeline identifies one pair of events that occurred.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6WeFbt_4fVJs3ddLQQPR2w.png" /><figcaption>Explainability Example</figcaption></figure><p>3. We are presenting the data at the fingertips of your teams. We can either feed insights into a chat tool of your choice, allow for forensic analysis through a web based console, feed it to an ITSM system such as ServiceNow or allow you to integrate it into any custom application using our APIs.</p><p><strong>To summarize</strong></p><p>We encourage you to build on all the hard work we have done to make <a href="https://www.ibm.com/cloud/cloud-pak-for-watson-aiops">Cloud Pak for Watson AIOps</a> an indispensable tool in the operations space, and therefore save your data scientists’ precious time allowing them to focus on your actual business problems.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=434129522962" width="1" height="1" alt=""><hr><p><a href="https://medium.com/ibm-cloud/why-aiops-is-better-than-hiring-a-data-scientist-434129522962">Why AIOps is better than hiring a data scientist</a> was originally published in <a href="https://medium.com/ibm-cloud">IBM Cloud</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>