11 Machine Learning in Pulsar

 

This chapter covers

  • Using Pulsar Functions to provide near real-time machine learning
  • Developing and maintaining the collection of inputs required by the machine learning model to provide a prediction
  • Executing PMML supported models inside a Pulsar Function
  • Executing non-PMML models inside a Pulsar Function

One of the primary goals of machine learning is the extraction of actionable insights from raw data. Having insights that are actionable means that you can use them to make strategic, data-driven decisions that result in a positive outcome for your business and customers. For instance, every time a customer places an order on the GottaEat application, we want to be able to provide the customer with an accurate estimated delivery time. In order to accomplish this, we would need to develop a machine learning model that predicts the delivery time of any given order based on a number of factors that allow us to make a more accurate decision.

11.1  Deploying Machine Learning Models

 
 
 

11.1.1    Batch Processing

 
 
 

11.1.2    Near Real-Time

 
 
 

11.2  Near Real-Time Model Deployment

 

11.3  Feature Vectors

 
 

11.3.1    Feature Stores

 

11.3.2    Feature Calculation

 
 

11.4  Delivery Time Estimation

 
 

11.4.1    Machine Learning Model Export

 
 

11.4.2    Feature Vector Mapping

 
 

11.4.3    Model Deployment

 
 

11.5  Neural Nets

 
 
 

11.5.1    Neural Net Training

 
 

11.5.2    Neural Net Deployment in Java

 
 
 
 

11.6  Summary

 
sitemap

Unable to load book!

The book could not be loaded.

(try again in a couple of minutes)

manning.com homepage
test yourself with a liveTest