In this presentation, we would like to share with you the journey behind the development of two machine-learning solutions with a real impact on practical real-life use cases.
How can we improve our advertising? How can we better target our potential customers? And how to define who our potential customers are? In the first part of the presentation, Nikola will guide you through the world of online advertising and show you how to apply machine learning techniques on online data to achieve less expensive and better-targeted advertising.
The second part of the presentation will be focused on computer vision. Marek will share with you his experience from the early stages of development of the Shelf Inspector, a computer vision-based monitoring tool for retailers. He will talk about its core object detection model, the Mask-RCNN, and the techniques that enhanced its performance. He will address the challenges faced and lessons learnt.
Nikola Valešová is a full-time data scientist keen on (not only) machine learning. As a FIT BUT graduate, she has a deep technical understanding of computer science and throughout her studies, she became keen on machine learning, data science, and image processing. During her internships at Red Hat and Thermo Fisher Scientific, she gained valuable experience in back-end programming in Python and C++ and image super-resolution using GANs (Generative Adversarial Networks).
Marek Lipán graduated in 2018 from the Institute of Economic Studies (IES) at Charles University with a specialization for Economic Theory and Modelling. In his theses, he focused on spatial econometrics and forecast ensemble learning. During his studies, he acquired several years of practical experience of data wrangling, analysing and modelling as a Credit Risk Analyst at Komerční Banka.
Currently, they work as Data Scientists for a Prague-based start-up DataSentics. Nikola's main responsibility is the development of predictive models for the optimization of online advertising and Marek has found his passion for computer vision and deep learning projects.
- Networking (ImpactHub)
Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and subsequent networking. Except of Prague, MLMU also spread to Brno, Bratislava and Košice.