Predictive APIs at APIdays Berlin
•
0 j'aime•1,988 vues
An introduction to Machine Learning and how to use it in your apps, thanks to Predictive APIs that abstract away part of the complexity. In this talk, I present the different types of Predictive APIs there are and I also show how one can create their own based on open source software.
Recommandé
Recommandé
Contenu connexe
En vedette
En vedette (13)
Similaire à Predictive APIs at APIdays Berlin
Similaire à Predictive APIs at APIdays Berlin (20)
Dernier
Dernier (20)
Predictive APIs at APIdays Berlin
- 6. –Mike Gualtieri, Principal Analyst at Forrester “Predictive apps are the next big thing in app development.”
- 7. –Waqar Hasan, VISA “Predictive is the ‘killer app’ for big data.”
- 8. 1. Machine Learning 2. Data
- 9. BUT
- 10. –McKinsey & Co. “A significant constraint on realizing value from big data will be a shortage of talent, particularly of people with deep expertise in statistics and machine learning.”
- 16. What the @#?~% is ML?
- 18. “How much is this house worth? — X $” -> Regression
- 19. Bedrooms Bathrooms Surface (foot²) Year built Type Price ($) 3 1 860 1950 house 565,000 3 1 1012 1951 house 2 1.5 968 1976 townhouse 447,000 4 1315 1950 house 648,000 3 2 1599 1964 house 3 2 987 1951 townhouse 790,000 1 1 530 2007 condo 122,000 4 2 1574 1964 house 835,000 4 2001 house 855,000 3 2.5 1472 2005 house 4 3.5 1714 2005 townhouse
- 20. Bedrooms Bathrooms Surface (foot²) Year built Type Price ($) 3 1 860 1950 house 565,000 3 1 1012 1951 house 2 1.5 968 1976 townhouse 447,000 4 1315 1950 house 648,000 3 2 1599 1964 house 3 2 987 1951 townhouse 790,000 1 1 530 2007 condo 122,000 4 2 1574 1964 house 835,000 4 2001 house 855,000 3 2.5 1472 2005 house 4 3.5 1714 2005 townhouse
- 24. “Which type of email is this? — Spam/Ham” -> Classification
- 25. WATCH OUT!
- 26. • Need examples of inputs AND outputs • Need enough examples
- 27. ??
- 28. Predictive APIs
- 29. The two phases of machine learning: • TRAIN a model • PREDICT with a model
- 30. The two methods of predictive APIs: • TRAIN a model • PREDICT with a model
- 31. The two methods of predictive APIs: • model = create_model(dataset) • predicted_output = create_prediction(model, new_input)
- 32. from bigml.api import BigML # create a model api = BigML() source = api.create_source('training_data.csv') dataset = api.create_dataset(source) model = api.create_model(dataset) # make a prediction prediction = api.create_prediction(model, new_input) print "Predicted output value: ",prediction['object']['output'] http://bit.ly/bigml_wakari
- 37. Algorithmic APIs: • ErsatzLabs -> deep learning • BigML -> decision trees • Wise.io -> random forests
- 39. Generic Predictive APIs: • BigML • Google Prediction API • Amazon • PredicSis • WolframCloud
- 41. Text classification APIs: • uClassify.com • MonkeyLearn.com • Cortical.io
- 43. Problem-specific Predictive APIs: • Churn: Framed.io, ChurnSpotter.io • Fraud detection: SiftScience.com • Lead scoring: Infer.com • Personal assistant (Siri): Wit.ai
- 45. Fixed-model Predictive APIs: • Text: Datumbox.com, Semantria.com • Vision: Indico, AlchemyAPI.com • Siri-like: maluuba.com
- 54. MLlib
- 57. • “Open source prediction server” • Based on Spark • Expose predictive models as (scalable & robust) APIs
- 58. = PAPI+
- 59. • Send (new) data • Send prediction queries
- 60. cli = predictionio.EventClient("<my_app_id>") cli.record_user_action_on_item("view","John","Item") eng = predictionio.EngineClient("<my_engine_url>") rec = eng.send_query({"uid":"John","n":5})
- 62. Use cases
- 63. • Increase e-commerce revenue with recos • Reduce attrition (“churn”) • Automate decision making • Predict real-estate prices w. open data • Predict crowds (SNCF & La Poste) • …