Anatomy of an ML Application: From Problem to Prediction
•
2 gefällt mir•574 views
1. The document discusses the anatomy of a machine learning application from defining the problem as a machine learning task, collecting and preparing data, building and evaluating models, and applying predictions. 2. It provides examples of real-world machine learning applications like predicting the success of startups and reducing turbulence on flights. 3. A key point is that machine learning applications involve more than just algorithms and require properly formulating the problem, engineering features from raw data, and iterative evaluation and improvement of models.
Empfohlen
Empfohlen
Weitere ähnliche Inhalte
Was ist angesagt?
Was ist angesagt? (15)
Ähnlich wie Anatomy of an ML Application: From Problem to Prediction
Ähnlich wie Anatomy of an ML Application: From Problem to Prediction (20)
Mehr von BigML, Inc
Mehr von BigML, Inc (20)
Kürzlich hochgeladen
Kürzlich hochgeladen (20)
Anatomy of an ML Application: From Problem to Prediction
- 1. 1st edition March 7-8, 2019
- 2. BigML, Inc Anatomy of an ML Application Machine Learning End-to-End Poul Petersen CIO, BigML !2
- 3. BigML, Inc #MLSEV Examples of ML Applications !3
- 4. BigML, Inc #MLSEV: Anatomy of an ML Application Real-world ML Applications !4 • Should you sign that NDA? • Upload the NDA to the website • The service uses Machine Learning to decide if the terms are fair https://ndalynn.com/
- 5. BigML, Inc #MLSEV: Anatomy of an ML Application Real-world ML Applications !5 • Gathers over 500 features about companies: • Crunchbase / Tweets / Patents / LinkedIn / etc. • Creates a label for success/failure: • IPO or acquisition = success • Bankruptcy or irrelevance = failure • Uses Machine Learning to build a model that predicts the success or failure of startups • And puts all of the information together into an investor dashboard https://preseries.com
- 6. BigML, Inc #MLSEV: Anatomy of an ML Application ML Adoption !6 "The gap for most companies isn’t that machine learning doesn’t work, but that they struggle to actually use it” • Why? • Too much focus on algorithms • Not enough focus on applying Machine
- 7. BigML, Inc #MLSEV: Anatomy of an ML Application Real-world ML Applications !7 https://thepointsguy.com/news/this-is-the-reason-you-arent-feeling-as-much-turbulence-on-delta-flights/ …collecting and analyzing “hundreds of thousands of data points,” with a plan to boost that to “millions,” creating a model that forecasts turbulence with a level of confidence heretofore unseen. Not Important: the algorithm!
- 8. BigML, Inc #MLSEV: Anatomy of an ML Application Machine Learning Evolution !8 Genesis Custom built Product Service Utility Academics & Researchers Scientists Developers Analysts Everyone 1950s 2000s 2011 2030 Commodity 2020 Ubiquity CertaintyUnknown Defined NovelCommon Weka, Scikit BigML, Azure ML, Amazon ML, Google Cloud ML1st Workshop on Machine Learning 1980 1980 • Machine Learning algorithms are fun to talk about: GPUs, NNs, etc • But the algorithms are largely a commodity already • Difficulty is knowing how to apply ML
- 9. BigML, Inc #MLSEV: Anatomy of an ML Application What is an ML Application !9 AIRLINE ORIGIN DESTINATION DEPARTURE DELAY DISTANCE ARRIVAL DELAY AS ANC SEA -11 1448,0 -22 AA LAX PBI -8 2330,0 -9 US SFO CLT -2 2296,0 5 AA LAX MIA -5 2342,0 -9 AS SEA ANC -1 1448,0 -21 DL SFO MSP -5 1589 8 NK LAS MSP -6 1299 -17 US LAX CLT 14 2125,0 -10 AA SFO DFW -11 1464,0 -13 DL LAS ATL 3 1747,0 -15 Finding patterns in data that can be used to make inferences… Predictive Models Consider: ML Definition
- 10. BigML, Inc #MLSEV: Anatomy of an ML Application What is an ML Application !10 AIRLINE ORIGIN DESTINATION DEPARTURE DELAY DISTANCE ARRIVAL DELAY AS ANC SEA -11 1448,0 -22 AA LAX PBI -8 2330,0 -9 US SFO CLT -2 2296,0 5 AA LAX MIA -5 2342,0 -9 AS SEA ANC -1 1448,0 -21 DL SFO MSP -5 1589 8 NK LAS MSP -6 1299 -17 US LAX CLT 14 2125,0 -10 AA SFO DFW -11 1464,0 -13 DL LAS ATL 3 1747,0 -15 Predictive Models • Where does this data come from? • How do you know what data? • Is the data formatted correctly? • What do you do with these models? • How do you combine them? • Will it work?
- 11. BigML, Inc #MLSEV: Anatomy of an ML Application Reality of a ML Application !11 Data Transformations Feature Engineering Data Collection Evaluation & Retraining Seen Unseen Predictive App
- 12. BigML, Inc #MLSEV: Anatomy of an ML Application Where to Start? !12 Step 1 Finish Step 2 - - - - - - - - ??? “Let’s predict customer churn!” “Here are the customers we predict will leave our service”
- 13. BigML, Inc #MLSEV: Anatomy of an ML Application Where to Start? !13 Step 1 Finish Step 2 - - - - - - - - ??? “Let’s detect fraud! “Here are the transactions we should stop immediately.
- 14. BigML, Inc #MLSEV: Anatomy of an ML Application ML Application Guide !14 • Remember: ML finds patterns in data enabling predictions about future events • This means you need data • What data depends on what you want to predict • And the data you have or can collect • Data needs to have patterns related to what you want to predict • Not magic: still can’t predict random events, lotteries, etc • Your problem statement needs to be specific • Not “Let’s predict churn” • But “Let’s predict churn by looking at the profile data of all previous customers of our service who have/have not churned” • This can be tricky… State the problem as an ML Task
- 15. BigML, Inc #MLSEV: Anatomy of an ML Application Where to Start? !15 Step 1 Finish “Let’s predict the Oscars!” “Here are the predicted winners” Step 2 - - - - - - - - ??? • Statement is not specific enough!!! • What data can we collect that predicts Oscar wins?
- 16. BigML, Inc #MLSEV: Anatomy of an ML Application Predicting the Oscars !16 • 6 out of 6 right! • 8 out of 8 actually, but probability of the predictions was “too low” • Adapted Screenplay • Original Screenplay BigML Scoresheet 2018 • 4 our of 8 major awards correctly predicted • Probabilities were lower this year • This is still significantly better than guessing 2019 How is this possible? Isn't the winner random?
- 17. BigML, Inc #MLSEV: Anatomy of an ML Application How an Oscar is Won !17 voting intention? 7,000+ members Insight: winning awards is not a random event!
- 18. BigML, Inc #MLSEV: Anatomy of an ML Application Let’s Predict Best Picture !18 Win London Critics Lose Writers Guild Win Directors Guild Win Golden Globe Win Bafta • These events are *not* independent • Similar, but not identical, factors contribute to each win… • We can expect a higher probability for Shape of Water to win Oscar ?Win?
- 19. BigML, Inc #MLSEV: Anatomy of an ML Application The Features !19 MOVIES AWARDS OBJECTIVE FIELDS • year • movie • movie_id • certificate • duration • genre • rate • metascore • synopsis • votes • gross • release_date • user_reviews • critic_reviews • popularity • awards_wins • awards_nomination s • release_date.year • release_date.mont h • release_date.day- of-month • release_date.day- of-week • Oscar_Best_Picture_nominated • Oscar_Best_Director_nominated • Oscar_Best_Actor_nominated • Oscar_Best_Actress_nominated • Oscar_Best_Supporting_Actor_nominated • Oscar_Best_Supporting_Actress_nominated • Oscar_Best_AdaScreen_nominated • Oscar_Best_OriScreen_nominated • Oscar_nominated • Oscar_nominated_categories • Golden_Globes_won • Golden_Globes_won_categories • Golden_Globes_nominated • Golden_Globes_nominated_categories • BAFTA_won • BAFTA_won_categories • BAFTA_nominated • BAFTA_nominated_categories • Screen_Actors_Guild_won • Screen_Actors_Guild_won_categories • Screen_Actors_Guild_nominated • Screen_Actors_Guild_nominated_categories • Critics_Choice_won • Critics_Choice_won_categories • Critics_Choice_nominated • Critics_Choice_nominated_categories • Directors_Guild_won • Directors_Guild_won_categories • Directors_Guild_nominated • Directors_Guild_nominated_categories • Producers_Guild_won • Producers_Guild_won_categories • Producers_Guild_nominated • Producers_Guild_nominated_categories • Art_Directors_Guild_won • Art_Directors_Guild_won_categories • Art_Directors_Guild_nominated • Art_Directors_Guild_nominated_categories • Writers_Guild_won • Writers_Guild_won_categories • Writers_Guild_nominated • Writers_Guild_nominated_categories • Costume_Designers_Guild_won • Costume_Designers_Guild_won_categories • Costume_Designers_Guild_nominated • Costume_Designers_Guild_nominated_categories • Online_Film_Television_Association_won • Online_Film_Television_Association_won_categories • Online_Film_Television_Association_nominated • Online_Film_Television_Association_nominated_catego ries • Online_Film_Critics_Society_won • Online_Film_Critics_Society_won_categories • Online_Film_Critics_Society_nominated • Online_Film_Critics_Society_nominated_categories • People_Choice_won • People_Choice_won_categories • People_Choice_nominated • People_Choice_nominated_categories • London_Critics_Circle_Film_won • London_Critics_Circle_Film_won_categories • London_Critics_Circle_Film_nominated • London_Critics_Circle_Film_nominated_categories • American_Cinema_Editors_won • American_Cinema_Editors_won_categories • American_Cinema_Editors_nominated • American_Cinema_Editors_nominated_categories • Hollywood_Film_won • Hollywood_Film_won_categories • Hollywood_Film_nominated • Hollywood_Film_nominated_categories • Austin_Film_Critics_Association_won • Austin_Film_Critics_Association_won_categories • Austin_Film_Critics_Association_nominated • Austin_Film_Critics_Association_nominated_categories • Denver_Film_Critics_Society_won • Denver_Film_Critics_Society_won_categories • Denver_Film_Critics_Society_nominated • Denver_Film_Critics_Society_nominated_categories • Boston_Society_of_Film_Critics_won • Boston_Society_of_Film_Critics_won_categories • Boston_Society_of_Film_Critics_nominated • Boston_Society_of_Film_Critics_nominated_categories • New_York_Film_Critics_Circle_won • New_York_Film_Critics_Circle_won_categories • New_York_Film_Critics_Circle_nominated • New_York_Film_Critics_Circle_nominated_categories • Los_Angeles_Film_Critics_Association_won • Los_Angeles_Film_Critics_Association_won_categorie s • Los_Angeles_Film_Critics_Association_nominated • Los_Angeles_Film_Critics_Association_nominated_cat egories • Oscar_Best_Picture_wo n • Oscar_Best_Director_w on • Oscar_Best_Actor_won • Oscar_Best_Actress_wo n • Oscar_Best_Supporting _Actor_won • Oscar_Best_Supporting _Actress_won Data pulled from IMDB… Engineered Features: Award items field Nomination Counts Awards Counts
- 20. BigML, Inc #MLSEV: Anatomy of an ML Application Oscars Dataset !20 DATASET is publicly available: https://bigml.com/user/academy_awards/gallery/dataset/ 5a94302592fb565ed400103b
- 21. BigML, Inc #MLSEV: Anatomy of an ML Application Oscars Example !21 • When specifying the problem, be as specific as possible • Not: “Let’s predict the Oscars” • Instead: “Let’s Predict the Oscars by correlating a series of award wins with the final Oscar win.” • The statement of the problem will guide the data required • Be aware of the cost of collecting the data versus the ROI: Tidbits and Lessons Learned….
- 22. BigML, Inc #MLSEV: Anatomy of an ML Application Ranking ML Applications !22 FEASIBILITY (incdataavailability/deccomplexity) ROI (impact and cost) - + + NO-BRAINERS START HERE NO-GO POSTPONABLE BRAINERS Thinking about an ML Application?
- 23. BigML, Inc #MLSEV: Anatomy of an ML Application Oscars Example !23 • When specifying the problem, be as specific as possible • Not: “Let’s predict the Oscars” • Instead: “Let’s Predict the Oscars by correlating a series of award wins with the final Oscar win.” • The statement of the problem will guide the data required • Be aware of the cost of collecting the data versus the ROI: • IMDB data is readily availble • We’re done right? • Nope. You can’t escape Feature Engineering • Items: BAFTA_won_categories = list of nominations • Aggregations: Nomination and Award counts • You can’t escape Feature Selection • Full user reviews costly to collect and not useful Tidbits and Lessons Learned…. Wait: How were you confident in the predictions?
- 24. BigML, Inc #MLSEV: Anatomy of an ML Application 2013 2016 119 variables Evaluating the Model !24 119 variables 2000 2016 119 variables 2000 2012Original Dataset Test Dataset Train Dataset • Ultimately, we want to use all the history to predict the winner for the current year • In order to evaluate success, we use a model built from 2000-2012 data to predict the winners for 2013-2016 • Built a separate Deepnet for each award category • Evaluation obtained a ROC AUC over 0.98 across all award categories Great: The model seems OK, what next?
- 25. BigML, Inc #MLSEV: Anatomy of an ML Application Effort of a ML Application !25 State the problem as an ML task Data wrangling Feature engineering Modeling and Evaluations Predictions Measure Results Data transformations ~80% effort ~5% effort ~5% effort This is only such low effort because of platforms like This is an area where is currently innovating Task ~10% effort Effort
- 26. BigML, Inc #MLSEV: Anatomy of an ML Application Reality Check !26 • All Machine Learned models are wrong • Real-world Machine Learning is iterative • End-to-end Machine Learning is compositional Three Important Concepts in Applying ML…
- 27. BigML, Inc #MLSEV: Anatomy of an ML Application End-to-end ML is Compositional !27 • Real-world problems • Solved by applying a combination of algorithms • Very rarely is it one-and-done
- 28. BigML, Inc #MLSEV: Anatomy of an ML Application Basic Workflow !28 SOURCE DATASET MODEL PREDICTION
- 29. BigML, Inc #MLSEV: Anatomy of an ML Application Feature Engineering !29 MODEL FILTERSOLD HOMES BATCH PREDICTION NEW FEATURES DATASET DEALS DATASET FILTERFORSALE HOMES NEW FEATURES
- 30. BigML, Inc #MLSEV: Anatomy of an ML Application End-to-end ML is Compositional !30 • Real-world problems • Solved by applying a combination of algorithms • Very rarely is it one-and-done • Each “step” is often multi-stage as well • Filtering/Cleaning data
- 31. BigML, Inc #MLSEV: Anatomy of an ML Application Anomaly Filter and Evaluate !31 DIABETES SOURCE DIABETES DATASET TRAIN SET TEST SET ALL MODEL CLEAN DATASET FILTER ALL MODEL ALL EVALUATION CLEAN EVALUATION COMPARE EVALUATIONS ANAOMALY DETECTOR
- 32. BigML, Inc #MLSEV: Anatomy of an ML Application Fixing Missing Values !32 Fix Missing Values in a “Meaningful” Way Filter Zeros Model insulin Predict insulin Select insulin Fixed Dataset Amended Dataset Original Dataset Clean Dataset
- 33. BigML, Inc #MLSEV: Anatomy of an ML Application End-to-end ML is Compositional !33 • Real-world problems • Solved by applying a combination of algorithms • Very rarely is it one-and-done • Each “step” is often multi-stage as well • Filtering/Cleaning data • Tuning a model for optimum performance
- 34. BigML, Inc #MLSEV: Anatomy of an ML Application Ensemble Tuning !34 ENSEMBLE N=20 EVALUATION SOURCE DATASET TRAINING TEST EVALUATIONEVALUATION ENSEMBLE N=10 ENSEMBLE N=1000 CHOOSE
- 35. BigML, Inc #MLSEV: Anatomy of an ML Application End-to-end ML is Compositional !35 • Real-world problems • Solved by applying a combination of algorithms • Very rarely is it one-and-done • Each “step” is often multi-stage as well • Filtering/Cleaning data • Tuning a model for optimum performance • Finding the best features
- 36. BigML, Inc #MLSEV: Anatomy of an ML Application Best-first Feature Selection !36 {F1} CHOOSE BEST S = {Fa} {F2} {F3} {F4} Fn S+{F1} S+{F2} S+{F3} S+{F4} S+{Fn-1} CHOOSE BEST S = {Fa, Fb} S+{F1} S+{F2} S+{F3} S+{F4} S+{Fn-1} CHOOSE BEST S = {Fa, Fb, Fc}
- 37. BigML, Inc #MLSEV: Anatomy of an ML Application End-to-end ML is Compositional !37 • Real-world problems • Solved by applying a combination of algorithms • Very rarely is it one-and-done • Each “step” is often multi-stage as well • Filtering/Cleaning data • Tuning a model for optimum performance • Finding the best features • May require models for several domains of knowledge • Multiple Training / Scoring
- 38. BigML, Inc #MLSEV: Anatomy of an ML Application AGGREGATED BY CARD AGGREGATED BY USER AGGREGATED BY PROFILE Multiple Domains !38 TRANSACTIONS ANOMALY BY CARD ANOMALY BY USER ANOMALY BY PROFILE ANOMALY SCORE ANOMALY SCORE ANOMALY SCORE NEW TRANSACTION APPROVED?
- 39. BigML, Inc #MLSEV: Anatomy of an ML Application End-to-end ML is Compositional !39 • Real-world problems • Solved by applying a combination of algorithms • Very rarely is it one-and-done • Each “step” is often multi-stage as well • Filtering/Cleaning data • Tuning a model for optimum performance • Finding the best features • May require models for several domains of knowledge • Multiple Training / Scoring • Even after deploying a model • Workflow to monitor performance, know when to retrain
- 40. BigML, Inc #MLSEV: Anatomy of an ML Application Model Retraining !40 TRAINING INPUT DATA PREDICTIONS ANOMALY SCORES OUTCOMES RETRAIN DATA
- 41. BigML, Inc #MLSEV: Anatomy of an ML Application Reality Check !41 • All Machine Learned models are wrong Three Important Concepts in Applying ML… • Real-world Machine Learning is iterative • End-to-end Machine Learning is compositional
- 42. BigML, Inc #MLSEV: Anatomy of an ML Application • Better features always beat better algorithms • Good algorithms already exist and are good enough • Tools like OptiML exist which can help optimize performance • The data is never good enough Tenets of Machine Learning !42 • All Machine Learned models are wrong • Real-world Machine Learning is iterative • End-to-end Machine Learning is compositional • Automation is better than hand tuning - you need an API! • When data changes quickly, training speed is more important than accuracy • Repeatability is superior to a single strong result • Problems are solved with workflows of algorithms • A ML solution is not real until it is in production • ML is here: Now we need 100,000x people applying ML , but some are useful