Recommendation is one of the most popular applications in machine learning (ML). In this workshop, we’ll show you how to build a movie recommendation model based on factorization machines — one of the built-in algorithms of Amazon SageMaker — and the popular MovieLens dataset.
4. Historical Data set
AGE GENDER LOCATION TEST DRIVE
24 M CENTRAL Y
42 F KOWLOON N
33 M LANTAU N
5. New Data Set
AGE GENDER LOCATION TEST DRIVE
24 M CENTRAL ?
42 F KOWLOON ?
33 M LANTAU ?
6. Query for Result
SELECT * FROM customers
WHERE
(age =24 AND gender =‘M’ AND location =‘Central’)
OR
(age =42 AND gender =‘F’ AND location =‘Kowloon’)
OR
(age =33 AND gender =‘M’ AND location =‘Lantau’)
OR
.. . .N
7. Query for Result
SELECT * FROM customers
WHERE
(age =24 AND gender =‘M’ AND location =‘Central’)
OR
(age =42 AND gender =‘F’ AND location =‘Kowloon’)
OR
(age =33 AND gender =‘M’ AND location =‘Lantau’)
OR
.. . .N
9. Supervised Machine Learning Process Flow
Age Gender Location TEST
DRIVE
30 M Central Y
40 M Chai Wan N
…. …… ….. …..
Learning
Algorithm
Model
Output
Historical Purchase Data
(Training Data)
Prediction
Age Gender Location TEST
DRIVE
35 F Lantau
39 M Taikoo
Input - New Unseen Data
10. Model Training - Performance Measurement
All Labeled Dataset
Training Data
70% 30%
Training
Test
Data
Evaluation
Result
Trial
Model
Accuracy
12. Machine Learning – When to Use It
You need ML if:
•Simple classification rules are inadequate
•Scalability is an issue with large number of datasets
You do not need ML if:
•You can predict the answers by using simple rules and computations
•You can program predetermined steps without needing any data driven
learning
15. Supervised Learning – How Machine Learn
Human intervention and validation required
e.g. Photo classification and tagging
Input
Label
Machine
Learning
Algorithm
Labrador
Prediction
Cat
Training Data
?
Label
Labrador
Adjust Model
16. Unsupervised Learning
No human intervention required
(e.g. Customer segmentation)
Input
Machine
Learning
Algorithm
Prediction
20. The broadest ML platform, that’s easiest to use, and
has the most customers
APPLICATION SERVICES
Amazon Lex
Amazon Polly
Amazon Comprehend
Amazon Translate
Amazon Transcribe
Amazon Rekognition Image
Amazon Rekognition Video
PLATFORM SERVICES
Amazon SageMaker
AWS DeepLens
FRAMEWORKS AND INTERFACES
AWS Deep Learning AMI
Apache MXNet
Caffe2
CNTK
PyTorch
TensorFlow
Theano
Torch
Gluon
Keras
Amazon ML Service
Amazon Mechanical Turk
21. APPLICATION SERVICES
Amazon Lex
Amazon Polly
Amazon Comprehend
Amazon Translate
Amazon Transcribe
Amazon Rekognition Image
Amazon Rekognition Video
PLATFORM SERVICES
Amazon SageMaker
AWS DeepLens
FRAMEWORKS AND INTERFACES
AWS Deep Learning AMI
Apache MXNet
Caffe2
CNTK
PyTorch
TensorFlow
Theano
Torch
Gluon
Keras
Amazon ML Service
Amazon Mechanical Turk
The broadest ML platform, that’s easiest to use, and
has the most customers