SmartData talks

Alexander Serbul 1C-Bitrix
Alexander Serbul
1C-Bitrix
Day 1 / 16:45  / Track 1 / RU /

Applied machine learning in e-commerce — scenarios and architectures of pilots and real-world projects

Presenting a number of company's pilots and real-world projects applying popular and "rare" algorithms of machine learning, as well as technical implementation on different platforms such as Java, PHP, Python using open libraries and a range of Amazon Web Services tools.

Read more
Artem Marinov Data-Centric Alliance
Artem Marinov
Data-Centric Alliance
Day 1 / 14:25  / Track 3 / RU /

Segment of 600 million users in real time every day. HBase/Kafka on the DMP service

Will be later

Read more
Artem Grigoriev Yandex
Artem Grigoriev
Yandex
Day 1 / 15:35  / Track 2 / RU /

Crowdsourcing: how to tame a crowd?

Will be later

Read more
Sergey Nikolenko PDMI RAS
Sergey Nikolenko
PDMI RAS
Day 1 / 14:25  / Track 1 / RU /

Deep convolutional networks to segment images

Will be later

Read more
Alexey Potapov ITMO
Alexey Potapov
ITMO
Day 1 / 15:35  / Track 1 / RU /

Deep learning, probabilistic programming and meta-estimation: point of intersection

Discussing generative and discriminative models' connections in terms of program specialization, their role within the framework of deep learning and probabilistic programming. Addressing neural Bayesian approach, neural probabilistic programming as an integration of two paradigms on an example of Edward library.

Read more
Alexander Sibiryakov Scrapinghub
Alexander Sibiryakov
Scrapinghub
Day 1 / 12:50  / Track 2 / RU /

Collection of contacts in bypass .com

This talk is about a distributed web-crawler for search and extraction of contact information from corporate websites.

Read more
Ivan Begtin Open Data, NGO Informational Culture
Ivan Begtin
Open Data, NGO Informational Culture
Day 1 / 10:30  / Track 2 / RU /

Open data. About the availability of state data and how to find them

Access to government data opens new opportunities for the businesses ready to create new products based on that data and improve existing ones, but it requires understanding of how data is collected, analyzed and published.

Read more
Dmitry Bugaychenko  Mail.ru
Dmitry Bugaychenko
Mail.ru
Day 1 / 11:40  / Track 2 / RU /

From click to predict and back: Data Science pipelines at OK

The talk covers different data processing and storage technologies from Hadoop ecosystem and more. If you are doing ML not just for fun, but also for profit, you might get some useful information from the talk.

Read more