Why APM Is Not the Same As ML Monitoring

Databricks
DatabricksDeveloper Marketing and Relations at MuleSoft
ML Monitoring is not APM
Cory A. Johannsen
Product Engineer, Verta Inc.
www.verta.ai
Agenda
▴ What is APM?
▴ What is ML monitoring?
▴ How ML monitoring and APM differ
▴ The unique needs of ML monitoring
▴ A very cool solution to model monitoring from Verta
About
https://www.verta.ai/product
- End-to-end MLOps platform for ML
model delivery, operations and
management
- Kubernetes-based, operations stack
for ML
- 23 years as a software engineer
- Embedded systems, enterprise
software, SaaS
- 6 years in APM working at scale
Feedback
Your feedback is important to us.
Don’t forget to rate and review the sessions.
What is APM?
What is APM?
▴ Application performance Monitoring
▴ Metrics
○ Name
○ Value
○ Labels
○ Timestamp
▴ Visualization
▴ Alerting
What do I care about monitoring in APM?
▴ Health
▴ Availability
▴ Performance
▴ Stability
▴ Notification
APM in practice
▴ Production operations
▴ Diagnostics and debugging
▴ Critical incident response
What is Model Monitoring?
▴ Know when models are failing
▴ Quickly find the root cause
▴ Close the loop by fast recovery
10
Ensuring model results are
consistently of high quality
*We refer to all latency, throughput etc. as model service health
▴ w/o ground truth, model
fails challenging to detect
▴ Need to monitor complex
statistical summaries
▴ Distributions, anomalies,
missing values, quantiles
etc.
▴ Often model-specific
▴ Intelligent detection
and alerting to
pre-emptively identify
issues and trigger
remediations
▴ Execute re-trains,
fallback models, and
human intervention.
11
Know when a model fails Close the loop
▴ A model is one part of a
inference pipeline
▴ Need global view of the
pipeline jungle to see
where the root issue
may be
Quickly find the root cause
How APM and ML monitoring align
▴ Error rate, Throughput, Latency
○ You need to know my production systems are
operational
▴ Visualization
○ You need to see change over time
▴ Alerting
○ You need to know when
something has gone wrong
(and only when something
has gone wrong)
What do you care about in ML Monitoring?
▴ Distribution
○ Training versus test
○ Iteration over iteration
○ Live prediction
▴ Drift
○ Change in Distribution over
time
How APM and ML monitoring differ
▴ Error Rate, Throughput, Latency
○ Necessary, no longer sufficient
▴ Not all work is production work
○ ML monitoring happens from the beginning
of the pipeline
▴ APM can tell you what is wrong
○ ML monitoring is about understanding why
What makes ML monitoring unique
▴ Quantitative analysis of model performance
○ Information you can use
▴ Controlled comparison of distributions
○ Repeatable
○ Reliable
○ Consistent
▴ Alerting on meaningful deviation
○ Actionable
○ Timely
○ Accurate
Only you know the shape of your data
▴ Every model and pipeline is different and specialized
○ You built them, you understand them
▴ You know what metrics and distributions are valuable
○ This is your model, you know the data and processes that created it
▴ You know the expected distributions
○ You can determine whether the behavior is correct
Only you know how to measure change
▴ Compare to reference set
○ Training, test, golden data set
▴ Compare to a baseline
○ Calculate a baseline from your data or production systems
▴ Compare to other
○ Use a comparison that makes sense in your domain
Only you know when a change matters
▴ You know your model and tolerances
▴ You know when a deviation is significant (or not!)
▴ You know when these conditions need to change
Verta understand model monitoring
▴ Designed for your workflows
▴ Easy integration to capture your monitoring data
▴ Visualize and understand your metrics, distributions, and drift
▴ Get alerted when you should - not otherwise
Introducing a generalized
framework for Model Monitoring
Concepts
▴ Monitored Entity: A reference name (e.g. model or pipeline) that you want to
monitor
▴ Profiler: A function that computes statistics about your data
▴ Summary: A collection of statistics about your data (output of profiler)
○ Samples: instance of a summary, i.e., a statistic
○ Labels: key-values attached to summary samples. Used for rich filtering and
aggregation
▴ Alerter: Triggered periodically, it can talk with the Verta API to fetch information
about summaries and identify if they look wrong
How does it work?
1. Define monitored entity: the entity to be monitored (e.g., model, data, pipeline)
2. Define summaries to monitor for the entity
3. Run profilers (manually or automatically) to produce summary samples
4. View samples, define alerts
5. Get alerted (e.g. via Slack)
6. Close the loop!
How does it work?
Time-series DB for
statistical summaries
...
Ground truth
Data/Model
Pipelines
Model (Live)
Remediation
- Retrain
- Rollback
- Human loop
Model (Batch)
Prediction
Log
Summary
▴ Performance monitoring is no longer sufficient for the needs of modern ML systems
○ Model monitoring starts at the beginning of the pipeline and continues through production
○ Batch and live can be addressed in the same framework
▴ Knowing something is wrong is not enough, you need to know why
▴ Timely actionable alerting is mandatory
▴ Building these tools on-site is difficult, error-prone, and expensive
▴ Spark is a fantastic tool to enable model monitoring
Monitor Your Models with Verta
▴ Visit monitoring.verta.ai today and see it in action
▴ Join our community
▴ Get more out of your models
▴ Get more out of your alerts
Thank you.
Cory A. Johannsen
Product Engineer, Verta Inc.
www.verta.ai
1 of 26

Recommended

Jeeves Grows Up: An AI Chatbot for Performance and Quality by
Jeeves Grows Up: An AI Chatbot for Performance and QualityJeeves Grows Up: An AI Chatbot for Performance and Quality
Jeeves Grows Up: An AI Chatbot for Performance and QualityDatabricks
260 views28 slides
Importance of ML Reproducibility & Applications with MLfLow by
Importance of ML Reproducibility & Applications with MLfLowImportance of ML Reproducibility & Applications with MLfLow
Importance of ML Reproducibility & Applications with MLfLowDatabricks
288 views29 slides
Re-imagine Data Monitoring with whylogs and Spark by
Re-imagine Data Monitoring with whylogs and SparkRe-imagine Data Monitoring with whylogs and Spark
Re-imagine Data Monitoring with whylogs and SparkDatabricks
551 views24 slides
The Critical Missing Component in the Production ML Stack by
The Critical Missing Component in the Production ML StackThe Critical Missing Component in the Production ML Stack
The Critical Missing Component in the Production ML StackDatabricks
66 views21 slides
FlorenceAI: Reinventing Data Science at Humana by
FlorenceAI: Reinventing Data Science at HumanaFlorenceAI: Reinventing Data Science at Humana
FlorenceAI: Reinventing Data Science at HumanaDatabricks
468 views28 slides
Model Monitoring at Scale with Apache Spark and Verta by
Model Monitoring at Scale with Apache Spark and VertaModel Monitoring at Scale with Apache Spark and Verta
Model Monitoring at Scale with Apache Spark and VertaDatabricks
360 views26 slides

More Related Content

What's hot

AI Modernization at AT&T and the Application to Fraud with Databricks by
AI Modernization at AT&T and the Application to Fraud with DatabricksAI Modernization at AT&T and the Application to Fraud with Databricks
AI Modernization at AT&T and the Application to Fraud with DatabricksDatabricks
587 views15 slides
Infrastructure Agnostic Machine Learning Workload Deployment by
Infrastructure Agnostic Machine Learning Workload DeploymentInfrastructure Agnostic Machine Learning Workload Deployment
Infrastructure Agnostic Machine Learning Workload DeploymentDatabricks
347 views38 slides
NLP Text Recommendation System Journey to Automated Training by
NLP Text Recommendation System Journey to Automated TrainingNLP Text Recommendation System Journey to Automated Training
NLP Text Recommendation System Journey to Automated TrainingDatabricks
176 views20 slides
Tensors Are All You Need: Faster Inference with Hummingbird by
Tensors Are All You Need: Faster Inference with HummingbirdTensors Are All You Need: Faster Inference with Hummingbird
Tensors Are All You Need: Faster Inference with HummingbirdDatabricks
268 views49 slides
Detecting Anomalous Behavior with Surveillance​ Analytics​ by
Detecting Anomalous Behavior with Surveillance​ Analytics​Detecting Anomalous Behavior with Surveillance​ Analytics​
Detecting Anomalous Behavior with Surveillance​ Analytics​Databricks
236 views16 slides
Data Science for Dummies - Data Engineering with Titanic dataset + Databricks... by
Data Science for Dummies - Data Engineering with Titanic dataset + Databricks...Data Science for Dummies - Data Engineering with Titanic dataset + Databricks...
Data Science for Dummies - Data Engineering with Titanic dataset + Databricks...Rodney Joyce
454 views24 slides

What's hot(20)

AI Modernization at AT&T and the Application to Fraud with Databricks by Databricks
AI Modernization at AT&T and the Application to Fraud with DatabricksAI Modernization at AT&T and the Application to Fraud with Databricks
AI Modernization at AT&T and the Application to Fraud with Databricks
Databricks587 views
Infrastructure Agnostic Machine Learning Workload Deployment by Databricks
Infrastructure Agnostic Machine Learning Workload DeploymentInfrastructure Agnostic Machine Learning Workload Deployment
Infrastructure Agnostic Machine Learning Workload Deployment
Databricks347 views
NLP Text Recommendation System Journey to Automated Training by Databricks
NLP Text Recommendation System Journey to Automated TrainingNLP Text Recommendation System Journey to Automated Training
NLP Text Recommendation System Journey to Automated Training
Databricks176 views
Tensors Are All You Need: Faster Inference with Hummingbird by Databricks
Tensors Are All You Need: Faster Inference with HummingbirdTensors Are All You Need: Faster Inference with Hummingbird
Tensors Are All You Need: Faster Inference with Hummingbird
Databricks268 views
Detecting Anomalous Behavior with Surveillance​ Analytics​ by Databricks
Detecting Anomalous Behavior with Surveillance​ Analytics​Detecting Anomalous Behavior with Surveillance​ Analytics​
Detecting Anomalous Behavior with Surveillance​ Analytics​
Databricks236 views
Data Science for Dummies - Data Engineering with Titanic dataset + Databricks... by Rodney Joyce
Data Science for Dummies - Data Engineering with Titanic dataset + Databricks...Data Science for Dummies - Data Engineering with Titanic dataset + Databricks...
Data Science for Dummies - Data Engineering with Titanic dataset + Databricks...
Rodney Joyce454 views
Feature drift monitoring as a service for machine learning models at scale by Noriaki Tatsumi
Feature drift monitoring as a service for machine learning models at scaleFeature drift monitoring as a service for machine learning models at scale
Feature drift monitoring as a service for machine learning models at scale
Noriaki Tatsumi178 views
ML-Ops: From Proof-of-Concept to Production Application by Hunter Carlisle
ML-Ops: From Proof-of-Concept to Production ApplicationML-Ops: From Proof-of-Concept to Production Application
ML-Ops: From Proof-of-Concept to Production Application
Hunter Carlisle96 views
Advanced Model Comparison and Automated Deployment Using ML by Databricks
Advanced Model Comparison and Automated Deployment Using MLAdvanced Model Comparison and Automated Deployment Using ML
Advanced Model Comparison and Automated Deployment Using ML
Databricks227 views
Ml infra at an early stage by Nick Handel
Ml infra at an early stageMl infra at an early stage
Ml infra at an early stage
Nick Handel209 views
Machine Learning In Production by Samir Bessalah
Machine Learning In ProductionMachine Learning In Production
Machine Learning In Production
Samir Bessalah5.8K views
Unified MLOps: Feature Stores & Model Deployment by Databricks
Unified MLOps: Feature Stores & Model DeploymentUnified MLOps: Feature Stores & Model Deployment
Unified MLOps: Feature Stores & Model Deployment
Databricks434 views
Operationalizing Edge Machine Learning with Apache Spark with Nisha Talagala ... by Databricks
Operationalizing Edge Machine Learning with Apache Spark with Nisha Talagala ...Operationalizing Edge Machine Learning with Apache Spark with Nisha Talagala ...
Operationalizing Edge Machine Learning with Apache Spark with Nisha Talagala ...
Databricks615 views
NLP-Focused Applied ML at Scale for Global Fleet Analytics at ExxonMobil by Databricks
NLP-Focused Applied ML at Scale for Global Fleet Analytics at ExxonMobilNLP-Focused Applied ML at Scale for Global Fleet Analytics at ExxonMobil
NLP-Focused Applied ML at Scale for Global Fleet Analytics at ExxonMobil
Databricks256 views
Machine learning model to production by Georg Heiler
Machine learning model to productionMachine learning model to production
Machine learning model to production
Georg Heiler4.4K views
Big Data at Speed by markgrover
Big Data at SpeedBig Data at Speed
Big Data at Speed
markgrover244 views
Oct 2011 CHADNUG Presentation on Hadoop by Josh Patterson
Oct 2011 CHADNUG Presentation on HadoopOct 2011 CHADNUG Presentation on Hadoop
Oct 2011 CHADNUG Presentation on Hadoop
Josh Patterson1.4K views
Strata parallel m-ml-ops_sept_2017 by Nisha Talagala
Strata parallel m-ml-ops_sept_2017Strata parallel m-ml-ops_sept_2017
Strata parallel m-ml-ops_sept_2017
Nisha Talagala491 views
Production ready big ml workflows from zero to hero daniel marcous @ waze by Ido Shilon
Production ready big ml workflows from zero to hero daniel marcous @ wazeProduction ready big ml workflows from zero to hero daniel marcous @ waze
Production ready big ml workflows from zero to hero daniel marcous @ waze
Ido Shilon1.8K views

Similar to Why APM Is Not the Same As ML Monitoring

Monitoring Distributed Systems by
Monitoring Distributed SystemsMonitoring Distributed Systems
Monitoring Distributed SystemsAleksandr Tavgen
94 views38 slides
#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf... by
#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf...#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf...
#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf...Agile Testing Alliance
231 views12 slides
Pipeline analytics concept for posting by
Pipeline analytics concept for postingPipeline analytics concept for posting
Pipeline analytics concept for postingMark Peco
639 views28 slides
Pipeline analytics concept for posting on linked in by
Pipeline analytics concept for posting on linked inPipeline analytics concept for posting on linked in
Pipeline analytics concept for posting on linked inMark Peco
501 views28 slides
Managing the Machine Learning Lifecycle with MLflow by
Managing the Machine Learning Lifecycle with MLflowManaging the Machine Learning Lifecycle with MLflow
Managing the Machine Learning Lifecycle with MLflowDatabricks
945 views46 slides
Vgo Sim And Opt by
Vgo Sim And OptVgo Sim And Opt
Vgo Sim And Optlksisemore
280 views8 slides

Similar to Why APM Is Not the Same As ML Monitoring(20)

#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf... by Agile Testing Alliance
#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf...#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf...
#ATAGTR2021 Presentation : "Use of AI and ML in Performance Testing" by Adolf...
Pipeline analytics concept for posting by Mark Peco
Pipeline analytics concept for postingPipeline analytics concept for posting
Pipeline analytics concept for posting
Mark Peco639 views
Pipeline analytics concept for posting on linked in by Mark Peco
Pipeline analytics concept for posting on linked inPipeline analytics concept for posting on linked in
Pipeline analytics concept for posting on linked in
Mark Peco501 views
Managing the Machine Learning Lifecycle with MLflow by Databricks
Managing the Machine Learning Lifecycle with MLflowManaging the Machine Learning Lifecycle with MLflow
Managing the Machine Learning Lifecycle with MLflow
Databricks945 views
Vgo Sim And Opt by lksisemore
Vgo Sim And OptVgo Sim And Opt
Vgo Sim And Opt
lksisemore280 views
Delivering BAM & BPM With Run-Time Integration by Nathaniel Palmer
Delivering BAM & BPM With Run-Time IntegrationDelivering BAM & BPM With Run-Time Integration
Delivering BAM & BPM With Run-Time Integration
Nathaniel Palmer507 views
Data drift and machine learning by Smita Agrawal
Data drift and machine learningData drift and machine learning
Data drift and machine learning
Smita Agrawal127 views
SAS Training session - By Pratima by Pratima Pandey
SAS Training session  -  By Pratima SAS Training session  -  By Pratima
SAS Training session - By Pratima
Pratima Pandey2.1K views
The Automation Firehose: Be Strategic and Tactical by Thomas Haver by QA or the Highway
The Automation Firehose: Be Strategic and Tactical by Thomas HaverThe Automation Firehose: Be Strategic and Tactical by Thomas Haver
The Automation Firehose: Be Strategic and Tactical by Thomas Haver
QA or the Highway243 views
Data drift and machine learning by Smita Agrawal
Data drift and machine learningData drift and machine learning
Data drift and machine learning
Smita Agrawal398 views
LIMS_ASQ.pptx by Arta Doci
LIMS_ASQ.pptxLIMS_ASQ.pptx
LIMS_ASQ.pptx
Arta Doci928 views
The Automation Firehose: Be Strategic & Tactical With Your Mobile & Web Testing by Perfecto by Perforce
The Automation Firehose: Be Strategic & Tactical With Your Mobile & Web TestingThe Automation Firehose: Be Strategic & Tactical With Your Mobile & Web Testing
The Automation Firehose: Be Strategic & Tactical With Your Mobile & Web Testing

More from Databricks

DW Migration Webinar-March 2022.pptx by
DW Migration Webinar-March 2022.pptxDW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptxDatabricks
4.3K views25 slides
Data Lakehouse Symposium | Day 1 | Part 1 by
Data Lakehouse Symposium | Day 1 | Part 1Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1Databricks
1.5K views43 slides
Data Lakehouse Symposium | Day 1 | Part 2 by
Data Lakehouse Symposium | Day 1 | Part 2Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2Databricks
743 views16 slides
Data Lakehouse Symposium | Day 4 by
Data Lakehouse Symposium | Day 4Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4Databricks
1.8K views74 slides
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop by
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of HadoopDatabricks
6.3K views64 slides
Democratizing Data Quality Through a Centralized Platform by
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized PlatformDatabricks
1.4K views36 slides

More from Databricks(20)

DW Migration Webinar-March 2022.pptx by Databricks
DW Migration Webinar-March 2022.pptxDW Migration Webinar-March 2022.pptx
DW Migration Webinar-March 2022.pptx
Databricks4.3K views
Data Lakehouse Symposium | Day 1 | Part 1 by Databricks
Data Lakehouse Symposium | Day 1 | Part 1Data Lakehouse Symposium | Day 1 | Part 1
Data Lakehouse Symposium | Day 1 | Part 1
Databricks1.5K views
Data Lakehouse Symposium | Day 1 | Part 2 by Databricks
Data Lakehouse Symposium | Day 1 | Part 2Data Lakehouse Symposium | Day 1 | Part 2
Data Lakehouse Symposium | Day 1 | Part 2
Databricks743 views
Data Lakehouse Symposium | Day 4 by Databricks
Data Lakehouse Symposium | Day 4Data Lakehouse Symposium | Day 4
Data Lakehouse Symposium | Day 4
Databricks1.8K views
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop by Databricks
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
5 Critical Steps to Clean Your Data Swamp When Migrating Off of Hadoop
Databricks6.3K views
Democratizing Data Quality Through a Centralized Platform by Databricks
Democratizing Data Quality Through a Centralized PlatformDemocratizing Data Quality Through a Centralized Platform
Democratizing Data Quality Through a Centralized Platform
Databricks1.4K views
Learn to Use Databricks for Data Science by Databricks
Learn to Use Databricks for Data ScienceLearn to Use Databricks for Data Science
Learn to Use Databricks for Data Science
Databricks1.6K views
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix by Databricks
The Function, the Context, and the Data—Enabling ML Ops at Stitch FixThe Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
The Function, the Context, and the Data—Enabling ML Ops at Stitch Fix
Databricks689 views
Stage Level Scheduling Improving Big Data and AI Integration by Databricks
Stage Level Scheduling Improving Big Data and AI IntegrationStage Level Scheduling Improving Big Data and AI Integration
Stage Level Scheduling Improving Big Data and AI Integration
Databricks850 views
Simplify Data Conversion from Spark to TensorFlow and PyTorch by Databricks
Simplify Data Conversion from Spark to TensorFlow and PyTorchSimplify Data Conversion from Spark to TensorFlow and PyTorch
Simplify Data Conversion from Spark to TensorFlow and PyTorch
Databricks1.8K views
Scaling your Data Pipelines with Apache Spark on Kubernetes by Databricks
Scaling your Data Pipelines with Apache Spark on KubernetesScaling your Data Pipelines with Apache Spark on Kubernetes
Scaling your Data Pipelines with Apache Spark on Kubernetes
Databricks2.1K views
Scaling and Unifying SciKit Learn and Apache Spark Pipelines by Databricks
Scaling and Unifying SciKit Learn and Apache Spark PipelinesScaling and Unifying SciKit Learn and Apache Spark Pipelines
Scaling and Unifying SciKit Learn and Apache Spark Pipelines
Databricks667 views
Sawtooth Windows for Feature Aggregations by Databricks
Sawtooth Windows for Feature AggregationsSawtooth Windows for Feature Aggregations
Sawtooth Windows for Feature Aggregations
Databricks606 views
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink by Databricks
Redis + Apache Spark = Swiss Army Knife Meets Kitchen SinkRedis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Redis + Apache Spark = Swiss Army Knife Meets Kitchen Sink
Databricks677 views
Raven: End-to-end Optimization of ML Prediction Queries by Databricks
Raven: End-to-end Optimization of ML Prediction QueriesRaven: End-to-end Optimization of ML Prediction Queries
Raven: End-to-end Optimization of ML Prediction Queries
Databricks450 views
Massive Data Processing in Adobe Using Delta Lake by Databricks
Massive Data Processing in Adobe Using Delta LakeMassive Data Processing in Adobe Using Delta Lake
Massive Data Processing in Adobe Using Delta Lake
Databricks719 views
Machine Learning CI/CD for Email Attack Detection by Databricks
Machine Learning CI/CD for Email Attack DetectionMachine Learning CI/CD for Email Attack Detection
Machine Learning CI/CD for Email Attack Detection
Databricks389 views
Intuitive & Scalable Hyperparameter Tuning with Apache Spark + Fugue by Databricks
Intuitive & Scalable Hyperparameter Tuning with Apache Spark + FugueIntuitive & Scalable Hyperparameter Tuning with Apache Spark + Fugue
Intuitive & Scalable Hyperparameter Tuning with Apache Spark + Fugue
Databricks348 views
Improving Apache Spark for Dynamic Allocation and Spot Instances by Databricks
Improving Apache Spark for Dynamic Allocation and Spot InstancesImproving Apache Spark for Dynamic Allocation and Spot Instances
Improving Apache Spark for Dynamic Allocation and Spot Instances
Databricks281 views
Hyperspace for Delta Lake by Databricks
Hyperspace for Delta LakeHyperspace for Delta Lake
Hyperspace for Delta Lake
Databricks561 views

Recently uploaded

Lack of communication among family.pptx by
Lack of communication among family.pptxLack of communication among family.pptx
Lack of communication among family.pptxahmed164023
15 views10 slides
[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init... by
[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init...[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init...
[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init...DataScienceConferenc1
5 views18 slides
PRIVACY AWRE PERSONAL DATA STORAGE by
PRIVACY AWRE PERSONAL DATA STORAGEPRIVACY AWRE PERSONAL DATA STORAGE
PRIVACY AWRE PERSONAL DATA STORAGEantony420421
7 views56 slides
Custom Tag Manager Templates by
Custom Tag Manager TemplatesCustom Tag Manager Templates
Custom Tag Manager TemplatesMarkus Baersch
30 views17 slides
LIVE OAK MEMORIAL PARK.pptx by
LIVE OAK MEMORIAL PARK.pptxLIVE OAK MEMORIAL PARK.pptx
LIVE OAK MEMORIAL PARK.pptxms2332always
7 views6 slides
apple.pptx by
apple.pptxapple.pptx
apple.pptxhoneybeeqwe
6 views15 slides

Recently uploaded(20)

Lack of communication among family.pptx by ahmed164023
Lack of communication among family.pptxLack of communication among family.pptx
Lack of communication among family.pptx
ahmed16402315 views
[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init... by DataScienceConferenc1
[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init...[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init...
[DSC Europe 23][Cryptica] Martin_Summer_Digital_central_bank_money_Ideas_init...
PRIVACY AWRE PERSONAL DATA STORAGE by antony420421
PRIVACY AWRE PERSONAL DATA STORAGEPRIVACY AWRE PERSONAL DATA STORAGE
PRIVACY AWRE PERSONAL DATA STORAGE
antony4204217 views
LIVE OAK MEMORIAL PARK.pptx by ms2332always
LIVE OAK MEMORIAL PARK.pptxLIVE OAK MEMORIAL PARK.pptx
LIVE OAK MEMORIAL PARK.pptx
ms2332always7 views
Data Journeys Hard Talk workshop final.pptx by info828217
Data Journeys Hard Talk workshop final.pptxData Journeys Hard Talk workshop final.pptx
Data Journeys Hard Talk workshop final.pptx
info82821711 views
CRM stick or twist workshop by info828217
CRM stick or twist workshopCRM stick or twist workshop
CRM stick or twist workshop
info82821714 views
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ... by DataScienceConferenc1
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...
Data about the sector workshop by info828217
Data about the sector workshopData about the sector workshop
Data about the sector workshop
info82821729 views
[DSC Europe 23][AI:CSI] Dragan Pleskonjic - AI Impact on Cybersecurity and P... by DataScienceConferenc1
[DSC Europe 23][AI:CSI]  Dragan Pleskonjic - AI Impact on Cybersecurity and P...[DSC Europe 23][AI:CSI]  Dragan Pleskonjic - AI Impact on Cybersecurity and P...
[DSC Europe 23][AI:CSI] Dragan Pleskonjic - AI Impact on Cybersecurity and P...
Ukraine Infographic_22NOV2023_v2.pdf by AnastosiyaGurin
Ukraine Infographic_22NOV2023_v2.pdfUkraine Infographic_22NOV2023_v2.pdf
Ukraine Infographic_22NOV2023_v2.pdf
AnastosiyaGurin1.4K views
Dr. Ousmane Badiane-2023 ReSAKSS Conference by AKADEMIYA2063
Dr. Ousmane Badiane-2023 ReSAKSS ConferenceDr. Ousmane Badiane-2023 ReSAKSS Conference
Dr. Ousmane Badiane-2023 ReSAKSS Conference
AKADEMIYA20635 views
4_4_WP_4_06_ND_Model.pptx by d6fmc6kwd4
4_4_WP_4_06_ND_Model.pptx4_4_WP_4_06_ND_Model.pptx
4_4_WP_4_06_ND_Model.pptx
d6fmc6kwd47 views
K-Drama Recommendation Using Python by FridaPutriassa
K-Drama Recommendation Using PythonK-Drama Recommendation Using Python
K-Drama Recommendation Using Python
FridaPutriassa5 views
CRM stick or twist.pptx by info828217
CRM stick or twist.pptxCRM stick or twist.pptx
CRM stick or twist.pptx
info82821711 views
Shreyas hospital statistics.pdf by samithavinal
Shreyas hospital statistics.pdfShreyas hospital statistics.pdf
Shreyas hospital statistics.pdf
samithavinal5 views

Why APM Is Not the Same As ML Monitoring

  • 1. ML Monitoring is not APM Cory A. Johannsen Product Engineer, Verta Inc. www.verta.ai
  • 2. Agenda ▴ What is APM? ▴ What is ML monitoring? ▴ How ML monitoring and APM differ ▴ The unique needs of ML monitoring ▴ A very cool solution to model monitoring from Verta
  • 3. About https://www.verta.ai/product - End-to-end MLOps platform for ML model delivery, operations and management - Kubernetes-based, operations stack for ML - 23 years as a software engineer - Embedded systems, enterprise software, SaaS - 6 years in APM working at scale
  • 4. Feedback Your feedback is important to us. Don’t forget to rate and review the sessions.
  • 6. What is APM? ▴ Application performance Monitoring ▴ Metrics ○ Name ○ Value ○ Labels ○ Timestamp ▴ Visualization ▴ Alerting
  • 7. What do I care about monitoring in APM? ▴ Health ▴ Availability ▴ Performance ▴ Stability ▴ Notification
  • 8. APM in practice ▴ Production operations ▴ Diagnostics and debugging ▴ Critical incident response
  • 9. What is Model Monitoring?
  • 10. ▴ Know when models are failing ▴ Quickly find the root cause ▴ Close the loop by fast recovery 10 Ensuring model results are consistently of high quality *We refer to all latency, throughput etc. as model service health
  • 11. ▴ w/o ground truth, model fails challenging to detect ▴ Need to monitor complex statistical summaries ▴ Distributions, anomalies, missing values, quantiles etc. ▴ Often model-specific ▴ Intelligent detection and alerting to pre-emptively identify issues and trigger remediations ▴ Execute re-trains, fallback models, and human intervention. 11 Know when a model fails Close the loop ▴ A model is one part of a inference pipeline ▴ Need global view of the pipeline jungle to see where the root issue may be Quickly find the root cause
  • 12. How APM and ML monitoring align ▴ Error rate, Throughput, Latency ○ You need to know my production systems are operational ▴ Visualization ○ You need to see change over time ▴ Alerting ○ You need to know when something has gone wrong (and only when something has gone wrong)
  • 13. What do you care about in ML Monitoring? ▴ Distribution ○ Training versus test ○ Iteration over iteration ○ Live prediction ▴ Drift ○ Change in Distribution over time
  • 14. How APM and ML monitoring differ ▴ Error Rate, Throughput, Latency ○ Necessary, no longer sufficient ▴ Not all work is production work ○ ML monitoring happens from the beginning of the pipeline ▴ APM can tell you what is wrong ○ ML monitoring is about understanding why
  • 15. What makes ML monitoring unique ▴ Quantitative analysis of model performance ○ Information you can use ▴ Controlled comparison of distributions ○ Repeatable ○ Reliable ○ Consistent ▴ Alerting on meaningful deviation ○ Actionable ○ Timely ○ Accurate
  • 16. Only you know the shape of your data ▴ Every model and pipeline is different and specialized ○ You built them, you understand them ▴ You know what metrics and distributions are valuable ○ This is your model, you know the data and processes that created it ▴ You know the expected distributions ○ You can determine whether the behavior is correct
  • 17. Only you know how to measure change ▴ Compare to reference set ○ Training, test, golden data set ▴ Compare to a baseline ○ Calculate a baseline from your data or production systems ▴ Compare to other ○ Use a comparison that makes sense in your domain
  • 18. Only you know when a change matters ▴ You know your model and tolerances ▴ You know when a deviation is significant (or not!) ▴ You know when these conditions need to change
  • 19. Verta understand model monitoring ▴ Designed for your workflows ▴ Easy integration to capture your monitoring data ▴ Visualize and understand your metrics, distributions, and drift ▴ Get alerted when you should - not otherwise
  • 20. Introducing a generalized framework for Model Monitoring
  • 21. Concepts ▴ Monitored Entity: A reference name (e.g. model or pipeline) that you want to monitor ▴ Profiler: A function that computes statistics about your data ▴ Summary: A collection of statistics about your data (output of profiler) ○ Samples: instance of a summary, i.e., a statistic ○ Labels: key-values attached to summary samples. Used for rich filtering and aggregation ▴ Alerter: Triggered periodically, it can talk with the Verta API to fetch information about summaries and identify if they look wrong
  • 22. How does it work? 1. Define monitored entity: the entity to be monitored (e.g., model, data, pipeline) 2. Define summaries to monitor for the entity 3. Run profilers (manually or automatically) to produce summary samples 4. View samples, define alerts 5. Get alerted (e.g. via Slack) 6. Close the loop!
  • 23. How does it work? Time-series DB for statistical summaries ... Ground truth Data/Model Pipelines Model (Live) Remediation - Retrain - Rollback - Human loop Model (Batch) Prediction Log
  • 24. Summary ▴ Performance monitoring is no longer sufficient for the needs of modern ML systems ○ Model monitoring starts at the beginning of the pipeline and continues through production ○ Batch and live can be addressed in the same framework ▴ Knowing something is wrong is not enough, you need to know why ▴ Timely actionable alerting is mandatory ▴ Building these tools on-site is difficult, error-prone, and expensive ▴ Spark is a fantastic tool to enable model monitoring
  • 25. Monitor Your Models with Verta ▴ Visit monitoring.verta.ai today and see it in action ▴ Join our community ▴ Get more out of your models ▴ Get more out of your alerts
  • 26. Thank you. Cory A. Johannsen Product Engineer, Verta Inc. www.verta.ai