SlideShare ist ein Scribd-Unternehmen logo
1 von 33
Disrupt the static nature of
BI with Predictive Anomaly
Detection
by Nir Kalish
Senior Director, Solution Engineering, Anodot
What is the problem?
Delayed business insights cost
companies millions of dollars
Real Time
Business Incident Detection
3
Business Incidents Use Cases
4
Getting Business Insights using traditional BI tools?
Monitoring Systems?
Maintenance,
not automated
False
Positive
No Real timeMillions of
metrics
%
0 1 0 1 1 0 1 0 1 0 1 0
5
6
Find the Anomaly… Using traditional BI tools
Dashboards
So How do we get Real Time Business Insight?
7
How to Track the Millions and Get the Insights?
Automated Anomaly Detection
Disrupting the static nature of BI
Aggregate, Detect, Group and Alert
8
9
What is Anomaly Detection?
Automatic Anomaly Detection in five Steps
Metrics
Collection –
Universal, scale
to millions
Normal
behavior
learning
Abnormal
behavior
learning
Behavioral
Topology
Learning
Feedback
Based Learning
1 2 3 4 5
10
Automatic Anomaly Detection in five Steps
Metrics
Collection –
Granular, scale
to millions
Normal
behavior
learning
Abnormal
behavior
learning
Behavioral
Topology
Learning
Feedback
Based Learning
1 2 3 4 5
11
Anomaly Detection in every granularity
Number of
Purchases
Product
Categor
y
Geo
Device
OS
Revenue
12
$ gift card
TV model
Phone model
Gift cards
Cell Phones
Electronics
US
EMEA
APJ
iOS
Windows
Android
Large Scale Anomaly Detection System Architecture
Kafka
Events
Queue
Anomaly
Grouping
Signals
Correlation
Map
Real-Time
Rollups Store
Cassandra
Anodotd
REST
WebApp
Online
Base Line
Learning
Aggregator
Elasticsearch
DWH S3
HADOOP/
Spark
HIVE
Offline
Learning
Management
&
Portal
Anodot-Web
User Mgmt
RDBMS
Customer DS
Agent
• 5.4 billion daily samples
• 120,000,000 metrics
• 240,000,000 models
• updated with each sample
• 500,000,000 correlation links
• Updated daily
• 14,000,000 seasonal models
• Updated daily
• 30 types of learning algorithms
• Metric classification,
seasonality detection, trend,
baseline models, clustering
algos, LSH, …
• And counting…
Automatic Anomaly Detection in five Steps
Metrics
Collection –
Universal, scale
to millions
Normal
behavior
learning
Abnormal
behavior
learning
Behavioral
Topology
Learning
Feedback
based learning
1 2 3 4 5
14
Static Thresholds versus Anomaly Based Alert
Anomaly Based Alert will find the problems hours before
the static based one
15
Normal Behaviour Modelling: Not so Simple…
16
Signal TypeSeasonal pattern Adapt to changes
17
Seasonality
Learning the normal behavior: Not all signals are created equal
Smooth Irregular
sampling
Multi Modal Sparse
Discrete “Step”
18
Step 1
Classify signal
to Category
Step 2
Match
Category with
Baseline
Distribution
and Algorithm
Metric types distribution
19
Distribution of metric types per industry
20
Update rate with adaptive online models: Avoiding pitfalls
21
What should be the learning rate?
Too Slow
Too Fast
Update rate with adaptive online models: Avoiding
pitfalls
22
What should be the learning rate?
“Al Dente”
Auto tuning required!
Automatic Anomaly Detection in five Steps
Metrics
Collection –
Universal, scale
to millions
Normal
behavior
learning
Abnormal
behavior
learning
Behavioral
Topology
Learning
Feedback
Based Learning
1 2 3 4 5
23
Abnormal behavior model
P(Anomaly Significance | Duration, Deviation)
90
70
50
30 2010
Abnormal Behaviour Learning
Abnormal Behaviour Learning
Anomaly
Score to
enable
correct
prioritization
of problems
25
Automatic Anomaly Detection in five Steps
Metrics
Collection –
Universal, scale
to millions
Normal
behavior
learning
Abnormal
behavior
learning
Behavioral
Topology
Learning
Feedback
Based Learning
1 2 3 4 5
26
Behavioral Topology Learning and Correlation
Viewing correlated metrics in context enables
correct problem identification
27
Price glitch – increase in
purchases / decrease in revenue
Automatic Anomaly Detection in five Steps
Metrics
Collection –
Universal, scale
to millions
Normal
behavior
learning
Abnormal
behavior
learning
Behavioral
Topology
Learning
Feedback
Based Learning
1 2 3 4 5
28
Feedback Based Learning
Enables continuance improvement of the machine learning process
29
Weekly anomaly stats: The importance of all steps
Based on 120,000,000 metrics
Normal
behavior
learning
Abnormal
behavior
learning
Behavioral
Topology
Learning
31
Anomaly Detection is every where
Social
Fintech
IT Ad-Tech
E-commerce
IOT
Business
Incident
Detection
32
Current Anodot Customers – Partial List
- Pedro Silva, Senior product, Credit Karma
It used to take us up to several days to identify an issue on a specific
page, offer, or service that was draining our revenues. Anodot
identifies when a metric increases or decreases in real time, so we
can resolve it quickly, before business suffers or revenue is lost.
THANK YOU

Weitere ähnliche Inhalte

Ähnlich wie Disrupt the static nature of BI with Predictive Anomaly Detection

Entering the Data Analytics industry
Entering the Data Analytics industryEntering the Data Analytics industry
Entering the Data Analytics industryGramener
 
How to Enter the Data Analytics Industry?
How to Enter the Data Analytics Industry?How to Enter the Data Analytics Industry?
How to Enter the Data Analytics Industry?Ganes Kesari
 
Using AI for online merchandising
Using AI for online merchandisingUsing AI for online merchandising
Using AI for online merchandisingSmart Insights
 
Towards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptxTowards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptxLuis775803
 
Cybersecurity Operations: Examining the State of the SOC
Cybersecurity Operations: Examining the State of the SOCCybersecurity Operations: Examining the State of the SOC
Cybersecurity Operations: Examining the State of the SOCFidelis Cybersecurity
 
Flaskdata - Observability for clinical data
Flaskdata - Observability for clinical dataFlaskdata - Observability for clinical data
Flaskdata - Observability for clinical dataFlaskdata.io
 
ThirdEye - LinkedIn's Business-wide monitoring platform
ThirdEye - LinkedIn's Business-wide monitoring platformThirdEye - LinkedIn's Business-wide monitoring platform
ThirdEye - LinkedIn's Business-wide monitoring platformAkshay Rai
 
Customer Intelligence & Analytics - Part I
Customer Intelligence & Analytics - Part ICustomer Intelligence & Analytics - Part I
Customer Intelligence & Analytics - Part IVivastream
 
Bio catch
Bio catchBio catch
Bio catchYanivt
 
Deep-Dive: Predicting Customer Behavior with Apigee Insights
Deep-Dive: Predicting Customer Behavior with Apigee InsightsDeep-Dive: Predicting Customer Behavior with Apigee Insights
Deep-Dive: Predicting Customer Behavior with Apigee InsightsApigee | Google Cloud
 
Smartcon 2015 – Automated Decisions in the Supply Chain
Smartcon 2015 – Automated Decisions in the Supply ChainSmartcon 2015 – Automated Decisions in the Supply Chain
Smartcon 2015 – Automated Decisions in the Supply ChainLars Trieloff
 
Automated Decision making with Predictive Applications – Big Data Hamburg
Automated Decision making with Predictive Applications – Big Data HamburgAutomated Decision making with Predictive Applications – Big Data Hamburg
Automated Decision making with Predictive Applications – Big Data HamburgLars Trieloff
 
Automated Decision Making with Predictive Applications – Big Data Düsseldorf
Automated Decision Making with Predictive Applications – Big Data DüsseldorfAutomated Decision Making with Predictive Applications – Big Data Düsseldorf
Automated Decision Making with Predictive Applications – Big Data DüsseldorfLars Trieloff
 
Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning
Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning
Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning ShiSh Shridhar
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language ProcessingYunyao Li
 
Machine Intelligence Powerpoint Presentation Slides
Machine Intelligence Powerpoint Presentation SlidesMachine Intelligence Powerpoint Presentation Slides
Machine Intelligence Powerpoint Presentation SlidesSlideTeam
 
Machine Intelligence PowerPoint Presentation Slides
Machine Intelligence PowerPoint Presentation SlidesMachine Intelligence PowerPoint Presentation Slides
Machine Intelligence PowerPoint Presentation SlidesSlideTeam
 
Retailers and Suppliers are Re-Tooling in Technology
Retailers and Suppliers are Re-Tooling in TechnologyRetailers and Suppliers are Re-Tooling in Technology
Retailers and Suppliers are Re-Tooling in TechnologySPI Conference
 
Tri State Final
Tri State FinalTri State Final
Tri State FinalSamWagner
 

Ähnlich wie Disrupt the static nature of BI with Predictive Anomaly Detection (20)

Entering the Data Analytics industry
Entering the Data Analytics industryEntering the Data Analytics industry
Entering the Data Analytics industry
 
How to Enter the Data Analytics Industry?
How to Enter the Data Analytics Industry?How to Enter the Data Analytics Industry?
How to Enter the Data Analytics Industry?
 
Using AI for online merchandising
Using AI for online merchandisingUsing AI for online merchandising
Using AI for online merchandising
 
Towards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptxTowards Responsible AI - KC.pptx
Towards Responsible AI - KC.pptx
 
Cybersecurity Operations: Examining the State of the SOC
Cybersecurity Operations: Examining the State of the SOCCybersecurity Operations: Examining the State of the SOC
Cybersecurity Operations: Examining the State of the SOC
 
Flaskdata - Observability for clinical data
Flaskdata - Observability for clinical dataFlaskdata - Observability for clinical data
Flaskdata - Observability for clinical data
 
ThirdEye - LinkedIn's Business-wide monitoring platform
ThirdEye - LinkedIn's Business-wide monitoring platformThirdEye - LinkedIn's Business-wide monitoring platform
ThirdEye - LinkedIn's Business-wide monitoring platform
 
Customer Intelligence & Analytics - Part I
Customer Intelligence & Analytics - Part ICustomer Intelligence & Analytics - Part I
Customer Intelligence & Analytics - Part I
 
Bio catch
Bio catchBio catch
Bio catch
 
Deep-Dive: Predicting Customer Behavior with Apigee Insights
Deep-Dive: Predicting Customer Behavior with Apigee InsightsDeep-Dive: Predicting Customer Behavior with Apigee Insights
Deep-Dive: Predicting Customer Behavior with Apigee Insights
 
APR Workshop 2010-M&E-Maria Donnat
APR Workshop 2010-M&E-Maria DonnatAPR Workshop 2010-M&E-Maria Donnat
APR Workshop 2010-M&E-Maria Donnat
 
Smartcon 2015 – Automated Decisions in the Supply Chain
Smartcon 2015 – Automated Decisions in the Supply ChainSmartcon 2015 – Automated Decisions in the Supply Chain
Smartcon 2015 – Automated Decisions in the Supply Chain
 
Automated Decision making with Predictive Applications – Big Data Hamburg
Automated Decision making with Predictive Applications – Big Data HamburgAutomated Decision making with Predictive Applications – Big Data Hamburg
Automated Decision making with Predictive Applications – Big Data Hamburg
 
Automated Decision Making with Predictive Applications – Big Data Düsseldorf
Automated Decision Making with Predictive Applications – Big Data DüsseldorfAutomated Decision Making with Predictive Applications – Big Data Düsseldorf
Automated Decision Making with Predictive Applications – Big Data Düsseldorf
 
Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning
Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning
Tastes, Trends, Touch Points - Understanding Shoppers Through Machine Learning
 
Explainability for Natural Language Processing
Explainability for Natural Language ProcessingExplainability for Natural Language Processing
Explainability for Natural Language Processing
 
Machine Intelligence Powerpoint Presentation Slides
Machine Intelligence Powerpoint Presentation SlidesMachine Intelligence Powerpoint Presentation Slides
Machine Intelligence Powerpoint Presentation Slides
 
Machine Intelligence PowerPoint Presentation Slides
Machine Intelligence PowerPoint Presentation SlidesMachine Intelligence PowerPoint Presentation Slides
Machine Intelligence PowerPoint Presentation Slides
 
Retailers and Suppliers are Re-Tooling in Technology
Retailers and Suppliers are Re-Tooling in TechnologyRetailers and Suppliers are Re-Tooling in Technology
Retailers and Suppliers are Re-Tooling in Technology
 
Tri State Final
Tri State FinalTri State Final
Tri State Final
 

Kürzlich hochgeladen

SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your BudgetHyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your BudgetEnjoy Anytime
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Hyundai Motor Group
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAndikSusilo4
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 

Kürzlich hochgeladen (20)

SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your BudgetHyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
Hyderabad Call Girls Khairatabad ✨ 7001305949 ✨ Cheap Price Your Budget
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & Application
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 

Disrupt the static nature of BI with Predictive Anomaly Detection

  • 1.
  • 2. Disrupt the static nature of BI with Predictive Anomaly Detection by Nir Kalish Senior Director, Solution Engineering, Anodot
  • 3. What is the problem? Delayed business insights cost companies millions of dollars Real Time Business Incident Detection 3
  • 5. Getting Business Insights using traditional BI tools? Monitoring Systems? Maintenance, not automated False Positive No Real timeMillions of metrics % 0 1 0 1 1 0 1 0 1 0 1 0 5
  • 6. 6 Find the Anomaly… Using traditional BI tools Dashboards
  • 7. So How do we get Real Time Business Insight? 7
  • 8. How to Track the Millions and Get the Insights? Automated Anomaly Detection Disrupting the static nature of BI Aggregate, Detect, Group and Alert 8
  • 9. 9 What is Anomaly Detection?
  • 10. Automatic Anomaly Detection in five Steps Metrics Collection – Universal, scale to millions Normal behavior learning Abnormal behavior learning Behavioral Topology Learning Feedback Based Learning 1 2 3 4 5 10
  • 11. Automatic Anomaly Detection in five Steps Metrics Collection – Granular, scale to millions Normal behavior learning Abnormal behavior learning Behavioral Topology Learning Feedback Based Learning 1 2 3 4 5 11
  • 12. Anomaly Detection in every granularity Number of Purchases Product Categor y Geo Device OS Revenue 12 $ gift card TV model Phone model Gift cards Cell Phones Electronics US EMEA APJ iOS Windows Android
  • 13. Large Scale Anomaly Detection System Architecture Kafka Events Queue Anomaly Grouping Signals Correlation Map Real-Time Rollups Store Cassandra Anodotd REST WebApp Online Base Line Learning Aggregator Elasticsearch DWH S3 HADOOP/ Spark HIVE Offline Learning Management & Portal Anodot-Web User Mgmt RDBMS Customer DS Agent • 5.4 billion daily samples • 120,000,000 metrics • 240,000,000 models • updated with each sample • 500,000,000 correlation links • Updated daily • 14,000,000 seasonal models • Updated daily • 30 types of learning algorithms • Metric classification, seasonality detection, trend, baseline models, clustering algos, LSH, … • And counting…
  • 14. Automatic Anomaly Detection in five Steps Metrics Collection – Universal, scale to millions Normal behavior learning Abnormal behavior learning Behavioral Topology Learning Feedback based learning 1 2 3 4 5 14
  • 15. Static Thresholds versus Anomaly Based Alert Anomaly Based Alert will find the problems hours before the static based one 15
  • 16. Normal Behaviour Modelling: Not so Simple… 16 Signal TypeSeasonal pattern Adapt to changes
  • 18. Learning the normal behavior: Not all signals are created equal Smooth Irregular sampling Multi Modal Sparse Discrete “Step” 18 Step 1 Classify signal to Category Step 2 Match Category with Baseline Distribution and Algorithm
  • 20. Distribution of metric types per industry 20
  • 21. Update rate with adaptive online models: Avoiding pitfalls 21 What should be the learning rate? Too Slow Too Fast
  • 22. Update rate with adaptive online models: Avoiding pitfalls 22 What should be the learning rate? “Al Dente” Auto tuning required!
  • 23. Automatic Anomaly Detection in five Steps Metrics Collection – Universal, scale to millions Normal behavior learning Abnormal behavior learning Behavioral Topology Learning Feedback Based Learning 1 2 3 4 5 23
  • 24. Abnormal behavior model P(Anomaly Significance | Duration, Deviation) 90 70 50 30 2010 Abnormal Behaviour Learning
  • 25. Abnormal Behaviour Learning Anomaly Score to enable correct prioritization of problems 25
  • 26. Automatic Anomaly Detection in five Steps Metrics Collection – Universal, scale to millions Normal behavior learning Abnormal behavior learning Behavioral Topology Learning Feedback Based Learning 1 2 3 4 5 26
  • 27. Behavioral Topology Learning and Correlation Viewing correlated metrics in context enables correct problem identification 27 Price glitch – increase in purchases / decrease in revenue
  • 28. Automatic Anomaly Detection in five Steps Metrics Collection – Universal, scale to millions Normal behavior learning Abnormal behavior learning Behavioral Topology Learning Feedback Based Learning 1 2 3 4 5 28
  • 29. Feedback Based Learning Enables continuance improvement of the machine learning process 29
  • 30. Weekly anomaly stats: The importance of all steps Based on 120,000,000 metrics Normal behavior learning Abnormal behavior learning Behavioral Topology Learning
  • 31. 31 Anomaly Detection is every where Social Fintech IT Ad-Tech E-commerce IOT Business Incident Detection
  • 32. 32 Current Anodot Customers – Partial List - Pedro Silva, Senior product, Credit Karma It used to take us up to several days to identify an issue on a specific page, offer, or service that was draining our revenues. Anodot identifies when a metric increases or decreases in real time, so we can resolve it quickly, before business suffers or revenue is lost.

Hinweis der Redaktion

  1. Focus on Metric collection
  2. Talking points: Ad tech tends to have KPIs that measure all the time and are smoother ---- a lot less irregular. Probably due to much heavier activity (with exchanges and ads – and end users that are a lot more). E-commerce KPIs are driven by users in the site/mobile/app --- so tends to be more of metrics that are not “smooth”. (17% difference from ad-tech and 5% less than all companies. Both have at least 50% metrics that are not “smooth” but require various other algos.