Ad-tech is one of the most demanding Hi-tech industries, where intelligent information systems need to be applied to data loads of tens of millions of requests per second. The Adform High Load Strategy is a unique event where state of the art Big Data and AI techniques will be presented together with real life production environments. This should be of special interest to Data Scientists, Engineers, Architects and any other people focused on modern data intensive and high load systems.
Software architect and team lead at Plasteli.net, where he works on solution for future network standards such as 200 and 400G Ethernet. His experience ranges from OS, network data-plane environments, high performance TCP/IP stacks, virtual routers, SDNs to implementation of scalable distributed systems. Among others he collaborated with AGH, Asahi Net, Juniper Networks, Mirantis, Motorola, QLogic, Semihalf.
Robert is a Senior IT Systems Engineer in Data Services team. He enjoys working on distributed systems and open source products. His preferred tech-stack includes Kubernetes, Ansible and Apache Kafka. Currently at Adform he is responsible for building and maintaining highly available and reliable infrastructure for Apache Kafka, RabbitMQ and Elasticsearch clusters. He wrote a lot of scripts that makes job done and leverage CLI rather than UI tools.
Dariusz is experienced with various cloud solutions, containers, automation, web deployment, databases and data platforms. In Adform currently focusing on Apache Mesos management and driving Aerospike clusters support, which runs 15+ million transactions per second & Redis databases solutions for smaller scale purposes.
Lukasz Maczewski Senior Data Scientist in DSP Algos team in Research Area. He is an ex-physicist, holding PhD in an experimental, particle physics and a senior data scientist in the Adform research team. In his current role, he is responsible for developing, deploying and maintaining real-time bidding (RTB) algorithms for online advertising. In his former job he was supporting analytics-based maintenance for General Electric turbofan jet engines. His specialization were advanced reliability models and diagnostics algorithms for failure detection. Łukasz has over 10 years of experience in research and broadly understood data science.
Has one foot in science and the other in engineering. An enthusiast of modern technologies specializing in .NET platform. In 2016, defended his doctoral thesis. Developed software used by the largest investment funds in the UK. Worked in a research project on image processing for Google. As Chief Scientific Officer was responsible for research & development of PlatformX - the artificial intelligence that writes software. A blogger (http://www.michalkomorowski.com/), author of scientific articles, speaker and holder of many certificates. Privately, a happy husband and father who loves travelling and books, also interested in survival and sport shooting.
Enthusiastic software engineer with several years of professional experience. .Net craftsman occasionally getting his hands dirty with devops and front-end tasks. Enjoys developing scalable, resilient and highly available systems.
Traveler, amateur photographer. He can't imagine his life without music, sports and IT literature.
Software engineer working on RealTimeBidding in Adform. Avid docker user. During the day he harnesses the power of NGINX, Lua and C# to handle millions of requests per second. Tries his best not to degrade his system's performance, occasionally even improving it. Before Adform he worked at Microsoft on Windows Phone 8.1 and Windows 10. During the night he does not fight crime as a masked vigilante, so don't ask him about it.
VP Research, AI & Analytics. For two and a half years associated with Adform, where he is leading the Research area. Previously he was the Chief Data Scientist at Allegro, where he managed the Data Science team supporting data driven e-commerce. Earlier, he gained experience in IT consulting (including Oracle, Accenture). In 2007 he defended his doctorate at Warsaw University of Technology, where he still teaches about Artificial Intelligence and Big Data.
Most of the contemporary services rely on processing huge amounts of data we all produce and consume increasingly each year. It is impossible to do that on a single machine and, in practice, it means hundreds of thousands of machines communicating with each other in a single datacentre alone. That communication needs to be fast. Really fast. Let's review the current state of the art in high-speed networking and have a glimpse of the future. Both its promises and challenges waiting to be addressed.
The Bid Landscape (BL) is one of the key components of the bidding strategy optimization in the area of the Real-Time Bidding (RTB). It allows for predicting RTB campaign performance with respect to its targeting and budget settings. The essential element of BL is the ability for predicting auction winning probability for the specific bid price. During presentation, we will go through technological and data science challenges regarding huge data streams we are facing.
