How to power up your product by machine learning with python micro-service

Dmitry Kisler

APIs Docker Machine-Learning Microservices

See in schedule

Most of data science articles cover details on how to build machine learning models, however only few describe how machine learning projects are being integrated into product (web-, or mobile app).

This tutorial will help aspiring data scientists to answer the following questions:

- how to kick-off a data science project
- how to facilitate integration of data science projects in the company
- how to organise end2end machine learning pipeline
- what are the tech stack and tools used for data science projects
- how to build and deploy an interface to integrate machine learning service into the product
- what are responsibilities of different teams working on machine learning services development

Participant will be building machine learning backend micro-service which is being integrated into a web application with pre-defined frontend.


Type: Training (180 mins); Python level: Beginner; Domain level: Beginner

Dmitry Kisler

Spark Networks Services GmbH

I am data scientist passioned about building data driven products. I have over 6 years of data science, data architecture and R&D experience across different industries from academical research to online dating and fintech. My natural curiosity, love to tech, physics and math/stats background, programming hands-on skills, attention to details, consultancy and management experience put me at unique spot in between top level business decision-makers, BI and engineering teams to bridge them and to facilitate monetisation of the business data by implementing analytical solutions.
Presently, I look after the data warehouse team of fulltimers and freelancers at one of the leading global IT companies where I’m focused on building new robust and scalable DWH and data science platform to disrupt dating industry via employing modern data analytics tools and machine learning techniques. In a spare time, I do consult start-ups on how to efficiently bring their data foundation up to scale.