�ݺ�ߣshows by User: tboubez

�ݺ�ߣshows by User: tboubez / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: tboubez / Wed, 19 Nov 2014 15:40:36 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: tboubez Five Things I Learned While Building Anomaly Detection Tools - Toufic Boubez - Metafor Software - LISA 2014 /slideshow/5-things-i-learned-toufic-boubez-metafor-lisa2014/41775172 5thingsilearned-touficboubez-metafor-lisa2014-141119154036-conversion-gate01
This is my presentation from LISA 2014 in Seattle on November 14, 2014. Most IT Ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this haystack of data and extracting signal from the noise is not easy and generates too many false positives. In this talk I will show some of the types of anomalies commonly found in dynamic data center environments and discuss the top 5 things I learned while building algorithms to find them. You will see how various Gaussian based techniques work (and why they don’t!), and we will go into some non-parametric methods that you can use to great advantage.]]>
This is my presentation from LISA 2014 in Seattle on November 14, 2014. Most IT Ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this haystack of data and extracting signal from the noise is not easy and generates too many false positives. In this talk I will show some of the types of anomalies commonly found in dynamic data center environments and discuss the top 5 things I learned while building algorithms to find them. You will see how various Gaussian based techniques work (and why they don’t!), and we will go into some non-parametric methods that you can use to great advantage.]]> Wed, 19 Nov 2014 15:40:36 GMT /slideshow/5-things-i-learned-toufic-boubez-metafor-lisa2014/41775172 tboubez@slideshare.net(tboubez) Five Things I Learned While Building Anomaly Detection Tools - Toufic Boubez - Metafor Software - LISA 2014 tboubez This is my presentation from LISA 2014 in Seattle on November 14, 2014. Most IT Ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this haystack of data and extracting signal from the noise is not easy and generates too many false positives. In this talk I will show some of the types of anomalies commonly found in dynamic data center environments and discuss the top 5 things I learned while building algorithms to find them. You will see how various Gaussian based techniques work (and why they don’t!), and we will go into some non-parametric methods that you can use to great advantage. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/5thingsilearned-touficboubez-metafor-lisa2014-141119154036-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds" /> This is my presentation from LISA 2014 in Seattle on November 14, 2014. Most IT Ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this haystack of data and extracting signal from the noise is not easy and generates too many false positives. In this talk I will show some of the types of anomalies commonly found in dynamic data center environments and discuss the top 5 things I learned while building algorithms to find them. You will see how various Gaussian based techniques work (and why they don’t!), and we will go into some non-parametric methods that you can use to great advantage.

Five Things I Learned While Building Anomaly Detection Tools - Toufic Boubez - Metafor Software - LISA 2014 from tboubez

]]> 3730 2 https://cdn.slidesharecdn.com/ss_thumbnails/5thingsilearned-touficboubez-metafor-lisa2014-141119154036-conversion-gate01-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Simple math for anomaly detection toufic boubez - metafor software - monitorama pdx 2014-05-05 /slideshow/simple-math-for-anomaly-detection-toufic-boubez-metafor-software-monitorama-pdx-20140505/34345294 simplemathforanomalydetection-touficboubez-metaforsoftware-monitoramapdx2014-05-05-140506112845-phpapp01
This is my presentation at Monitorama PDX in Portland on May 5, 2014 Simple math to get some signal out of your noisy sea of data You’ve instrumented your system and application to the hilt. You can now “measure all the things”. Your team has set up thousands of metrics collecting millions of data points a day. Now what? Most IT ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this mountain of data and extracting signal from the noise is not easy. The choice of what analytic method to use ranges from simple statistical analysis to sophisticated machine learning techniques. And one algorithm doesn’t fit all data. ]]>
This is my presentation at Monitorama PDX in Portland on May 5, 2014 Simple math to get some signal out of your noisy sea of data You’ve instrumented your system and application to the hilt. You can now “measure all the things”. Your team has set up thousands of metrics collecting millions of data points a day. Now what? Most IT ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this mountain of data and extracting signal from the noise is not easy. The choice of what analytic method to use ranges from simple statistical analysis to sophisticated machine learning techniques. And one algorithm doesn’t fit all data. ]]> Tue, 06 May 2014 11:28:45 GMT /slideshow/simple-math-for-anomaly-detection-toufic-boubez-metafor-software-monitorama-pdx-20140505/34345294 tboubez@slideshare.net(tboubez) Simple math for anomaly detection toufic boubez - metafor software - monitorama pdx 2014-05-05 tboubez This is my presentation at Monitorama PDX in Portland on May 5, 2014 Simple math to get some signal out of your noisy sea of data You’ve instrumented your system and application to the hilt. You can now “measure all the things”. Your team has set up thousands of metrics collecting millions of data points a day. Now what? Most IT ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this mountain of data and extracting signal from the noise is not easy. The choice of what analytic method to use ranges from simple statistical analysis to sophisticated machine learning techniques. And one algorithm doesn’t fit all data. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/simplemathforanomalydetection-touficboubez-metaforsoftware-monitoramapdx2014-05-05-140506112845-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> This is my presentation at Monitorama PDX in Portland on May 5, 2014 Simple math to get some signal out of your noisy sea of data You’ve instrumented your system and application to the hilt. You can now “measure all the things”. Your team has set up thousands of metrics collecting millions of data points a day. Now what? Most IT ops teams only keep an eye on a small fraction of the metrics they collect because analyzing this mountain of data and extracting signal from the noise is not easy. The choice of what analytic method to use ranges from simple statistical analysis to sophisticated machine learning techniques. And one algorithm doesn’t fit all data.

Simple math for anomaly detection toufic boubez - metafor software - monitorama pdx 2014-05-05 from tboubez

]]> 8779 10 https://cdn.slidesharecdn.com/ss_thumbnails/simplemathforanomalydetection-touficboubez-metaforsoftware-monitoramapdx2014-05-05-140506112845-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Velocity Europe 2013: Beyond Pretty Charts: Analytics for the cloud infrastructure. /slideshow/beyond-pretty-charts-toufic-boubez-metafor-software-20131115/28310872 beyondprettycharts-touficboubez-metaforsoftware-2013-11-15-131116060026-phpapp02
My presentation from Velocity Europe 2013 in London: Beyond Pretty Charts…. Analytics for the cloud infrastructure. IT Ops collect tons of data on the status of their data center or cloud environment. Much of that data ends up as graphs on big screens so ops folks can keep an eye on the behavior of their systems. But unless a threshold is crossed, behavioral issues will often fall through the cracks. Thresholds are reactive, and humans are, well, human. Applying analytics and machine learning to detect anomalies in dynamic infrastructure environments can catch these behavioral changes before they become critical. Current tools used to monitor web environments rely on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Thus interest in applying analytics and machine learning to predict and detect anomalies in these dynamic environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns.]]>
My presentation from Velocity Europe 2013 in London: Beyond Pretty Charts…. Analytics for the cloud infrastructure. IT Ops collect tons of data on the status of their data center or cloud environment. Much of that data ends up as graphs on big screens so ops folks can keep an eye on the behavior of their systems. But unless a threshold is crossed, behavioral issues will often fall through the cracks. Thresholds are reactive, and humans are, well, human. Applying analytics and machine learning to detect anomalies in dynamic infrastructure environments can catch these behavioral changes before they become critical. Current tools used to monitor web environments rely on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Thus interest in applying analytics and machine learning to predict and detect anomalies in these dynamic environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns.]]> Sat, 16 Nov 2013 06:00:26 GMT /slideshow/beyond-pretty-charts-toufic-boubez-metafor-software-20131115/28310872 tboubez@slideshare.net(tboubez) Velocity Europe 2013: Beyond Pretty Charts: Analytics for the cloud infrastructure. tboubez My presentation from Velocity Europe 2013 in London: Beyond Pretty Charts…. Analytics for the cloud infrastructure. IT Ops collect tons of data on the status of their data center or cloud environment. Much of that data ends up as graphs on big screens so ops folks can keep an eye on the behavior of their systems. But unless a threshold is crossed, behavioral issues will often fall through the cracks. Thresholds are reactive, and humans are, well, human. Applying analytics and machine learning to detect anomalies in dynamic infrastructure environments can catch these behavioral changes before they become critical. Current tools used to monitor web environments rely on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Thus interest in applying analytics and machine learning to predict and detect anomalies in these dynamic environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/beyondprettycharts-touficboubez-metaforsoftware-2013-11-15-131116060026-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> My presentation from Velocity Europe 2013 in London: Beyond Pretty Charts…. Analytics for the cloud infrastructure. IT Ops collect tons of data on the status of their data center or cloud environment. Much of that data ends up as graphs on big screens so ops folks can keep an eye on the behavior of their systems. But unless a threshold is crossed, behavioral issues will often fall through the cracks. Thresholds are reactive, and humans are, well, human. Applying analytics and machine learning to detect anomalies in dynamic infrastructure environments can catch these behavioral changes before they become critical. Current tools used to monitor web environments rely on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Thus interest in applying analytics and machine learning to predict and detect anomalies in these dynamic environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns.

Velocity Europe 2013: Beyond Pretty Charts: Analytics for the cloud infrastructure. from tboubez

]]> 2465 4 https://cdn.slidesharecdn.com/ss_thumbnails/beyondprettycharts-touficboubez-metaforsoftware-2013-11-15-131116060026-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation White http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Data centre analytics toufic boubez-metafor-dev ops days vancouver-2013-10-25 /slideshow/data-centre-analytics-toufic-boubezmetafordev-ops-days-vancouver20131025/27794950 datacentreanalytics-touficboubez-metafor-devopsdaysvancouver-2013-10-25-131031192455-phpapp01
Vancouver DevOps Days 25 October 2013 IT Ops collect a ton of data and produce reams of graphs to monitor systems and applications. Getting the right signal out of all that noise however is getting tougher and tougher. The traditional techniques to deal with such metrics, whether threshold-based or very simple statistical methods that were developed to deal with stable, static manufacturing processes, are failing in today’s dynamic environment. Interest in applying more advanced analytics and machine learning to detect anomalies is gaining steam but understanding which algorithms should be used to identify and predict anomalies without producing more false positives is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Overview of some current simple statistical methods and their weaknesses Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns.]]>
Vancouver DevOps Days 25 October 2013 IT Ops collect a ton of data and produce reams of graphs to monitor systems and applications. Getting the right signal out of all that noise however is getting tougher and tougher. The traditional techniques to deal with such metrics, whether threshold-based or very simple statistical methods that were developed to deal with stable, static manufacturing processes, are failing in today’s dynamic environment. Interest in applying more advanced analytics and machine learning to detect anomalies is gaining steam but understanding which algorithms should be used to identify and predict anomalies without producing more false positives is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Overview of some current simple statistical methods and their weaknesses Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns.]]> Thu, 31 Oct 2013 19:24:55 GMT /slideshow/data-centre-analytics-toufic-boubezmetafordev-ops-days-vancouver20131025/27794950 tboubez@slideshare.net(tboubez) Data centre analytics toufic boubez-metafor-dev ops days vancouver-2013-10-25 tboubez Vancouver DevOps Days 25 October 2013 IT Ops collect a ton of data and produce reams of graphs to monitor systems and applications. Getting the right signal out of all that noise however is getting tougher and tougher. The traditional techniques to deal with such metrics, whether threshold-based or very simple statistical methods that were developed to deal with stable, static manufacturing processes, are failing in today’s dynamic environment. Interest in applying more advanced analytics and machine learning to detect anomalies is gaining steam but understanding which algorithms should be used to identify and predict anomalies without producing more false positives is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Overview of some current simple statistical methods and their weaknesses Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/datacentreanalytics-touficboubez-metafor-devopsdaysvancouver-2013-10-25-131031192455-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Vancouver DevOps Days 25 October 2013 IT Ops collect a ton of data and produce reams of graphs to monitor systems and applications. Getting the right signal out of all that noise however is getting tougher and tougher. The traditional techniques to deal with such metrics, whether threshold-based or very simple statistical methods that were developed to deal with stable, static manufacturing processes, are failing in today’s dynamic environment. Interest in applying more advanced analytics and machine learning to detect anomalies is gaining steam but understanding which algorithms should be used to identify and predict anomalies without producing more false positives is not so easy. This talk will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data’s characteristics The two main approaches for analyzing operations data: parametric and non-parametric methods Overview of some current simple statistical methods and their weaknesses Simple data transformations that can give you powerful results By the end of this talk, attendees will understand the pros and cons of the key statistical analysis techniques and walk away with examples as well as practical rules of thumb and usage patterns.

Data centre analytics toufic boubez-metafor-dev ops days vancouver-2013-10-25 from tboubez

]]> 2007 2 https://cdn.slidesharecdn.com/ss_thumbnails/datacentreanalytics-touficboubez-metafor-devopsdaysvancouver-2013-10-25-131031192455-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Beyond pretty charts, Analytics for the rest of us. Toufic Boubez DevOps Days Silicon Valley 2013-06-22 /slideshow/beyond-pretty-charts-toufic-boubezmetafordev-ops-days-silicon-valley20130622/23481610 beyondprettycharts-touficboubez-metafor-devopsdayssiliconvalley-2013-06-22-130625172049-phpapp02
Current monitoring tools are clearly reaching the limit of their capabilities. That's because these tools are based on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Interest in applying analytics and machine learning to detect anomalies in dynamic web environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk builds on an Open Space discussion that was started at DevOps Days Austin. We will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data and the two main approaches for analyzing operations data: parametric and non-parametric methods The importance of context Simple data transformations that can give you powerful results]]>
Current monitoring tools are clearly reaching the limit of their capabilities. That's because these tools are based on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Interest in applying analytics and machine learning to detect anomalies in dynamic web environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk builds on an Open Space discussion that was started at DevOps Days Austin. We will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data and the two main approaches for analyzing operations data: parametric and non-parametric methods The importance of context Simple data transformations that can give you powerful results]]> Tue, 25 Jun 2013 17:20:48 GMT /slideshow/beyond-pretty-charts-toufic-boubezmetafordev-ops-days-silicon-valley20130622/23481610 tboubez@slideshare.net(tboubez) Beyond pretty charts, Analytics for the rest of us. Toufic Boubez DevOps Days Silicon Valley 2013-06-22 tboubez Current monitoring tools are clearly reaching the limit of their capabilities. That's because these tools are based on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Interest in applying analytics and machine learning to detect anomalies in dynamic web environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk builds on an Open Space discussion that was started at DevOps Days Austin. We will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data and the two main approaches for analyzing operations data: parametric and non-parametric methods The importance of context Simple data transformations that can give you powerful results <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/beyondprettycharts-touficboubez-metafor-devopsdayssiliconvalley-2013-06-22-130625172049-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> Current monitoring tools are clearly reaching the limit of their capabilities. That's because these tools are based on fundamental assumptions that are no longer true such as assuming that the underlying system being monitored is relatively static or that the behavioral limits of these systems can be defined by static rules and thresholds. Interest in applying analytics and machine learning to detect anomalies in dynamic web environments is gaining steam. However, understanding which algorithms should be used to identify and predict anomalies accurately within all that data we generate is not so easy. This talk builds on an Open Space discussion that was started at DevOps Days Austin. We will begin with a brief definition of the types of anomalies commonly found in dynamic data center environments and then discuss some of the key elements to consider when thinking about anomaly detection such as: Understanding your data and the two main approaches for analyzing operations data: parametric and non-parametric methods The importance of context Simple data transformations that can give you powerful results

Beyond pretty charts, Analytics for the rest of us. Toufic Boubez DevOps Days Silicon Valley 2013-06-22 from tboubez

]]> 3389 2 https://cdn.slidesharecdn.com/ss_thumbnails/beyondprettycharts-touficboubez-metafor-devopsdayssiliconvalley-2013-06-22-130625172049-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://public.slidesharecdn.com/v2/images/profile-picture.png https://cdn.slidesharecdn.com/ss_thumbnails/5thingsilearned-touficboubez-metafor-lisa2014-141119154036-conversion-gate01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/5-things-i-learned-toufic-boubez-metafor-lisa2014/41775172 Five Things I Learned ... https://cdn.slidesharecdn.com/ss_thumbnails/simplemathforanomalydetection-touficboubez-metaforsoftware-monitoramapdx2014-05-05-140506112845-phpapp01-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/simple-math-for-anomaly-detection-toufic-boubez-metafor-software-monitorama-pdx-20140505/34345294 Simple math for anomal... https://cdn.slidesharecdn.com/ss_thumbnails/beyondprettycharts-touficboubez-metaforsoftware-2013-11-15-131116060026-phpapp02-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/beyond-pretty-charts-toufic-boubez-metafor-software-20131115/28310872 Velocity Europe 2013: ...