How to deploy machine learning models into production
Data scientists spend a lot of time on data cleaning and munging, so that they can finally start with the fun part of their job: building models. After you have engineered the features and tested different models, you see how the prediction performance improves. However, the job is not done when you have a high performing model. The deployment of your models is a crucial step in the overall workflow and it is the point in time when your models actually become useful to your company.
In this session you will learn about various possibilities and best practices to bring machine learning models into production environments. The goal is not only to make live prediction calls or have the models available as REST API, but also what needs to be considered to maintain them. This talk will focus on solutions with Python (flask, Cloud Foundry, Docker, and more) and the well established ML packages such as Spark MLlib, scikit-learn, and xgboost, but the concepts can be easily transferred to other languages and frameworks.
Speaker
SUMIT GOYAL
Software Engineer
IBM
Видео How to deploy machine learning models into production канала DataWorks Summit
In this session you will learn about various possibilities and best practices to bring machine learning models into production environments. The goal is not only to make live prediction calls or have the models available as REST API, but also what needs to be considered to maintain them. This talk will focus on solutions with Python (flask, Cloud Foundry, Docker, and more) and the well established ML packages such as Spark MLlib, scikit-learn, and xgboost, but the concepts can be easily transferred to other languages and frameworks.
Speaker
SUMIT GOYAL
Software Engineer
IBM
Видео How to deploy machine learning models into production канала DataWorks Summit
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Machine Learning Performance Experiments with Spark MIIibNetwork Reference Architecture for Hadoop- Validated and Tested ApproachDataWorks Summit 2018 San Jose Day 2 KeynoteKarta an ETL Framework to process High Volume Data SetsDay two keynotesHarnessing the Power of Big Data at Freddie MacHadoop Event Notification SystemLeveraging Hadoop to defend against improvised threatsBreathing New Life into Apache Oozie with Apache Ambari Workflow ManagerBI on Big Data with instant response times at VerizonBig data processing meets non-volatile memory: opportunities and challengesStream Scaling in PravegaScott Burke Keynote Hadoop Summit 2012Low Latency OLAP with Hadoop and HBase.movPractical experiences using Atlas and Ranger to implement GDPRNot only Hadoop – the DAG ShowdownHelp Hadoop survive the 300 million block barrier and then back it up0604 Hbase Low Latency0605 Hadoop REST API Security with the Apache Knox GatewayPractice of large Hadoop cluster in China MobileHow to Ingest 16 Billion Records Per Day into your Hadoop Environment