Past Meetup

Search engine design and interactive system optimization

This Meetup is past

69 people went

Every last Friday of the month

Location image of event venue

Details

This Friday we'll have two talks followed by drinks. Our industrial speaker is Wouter Alink, a Search Engine Architect at Spinque. He will talk about the search engine design process at Spinque. Our academic speaker is Julia Kiseleva, Postdoctoral Researcher at the University of Amsterdam. She will talk about optimizing interactive systems with data-driven objectives.

Program:

16:00-16:30 Wouter Alink

16:30-17:00 Julia Kiseleva

17:00-18:00 Drinks and snacks

Details:

Wouter Alink - Search engine design

At Spinque we build tools to support the information specialist in the search engine design process. Various other roles are involved in this process: the data engineer, the information retrieval expert, the web developer. In this talk I will present how our software has evolved over the last couple of years to better separate and support these roles within the search engine design process.

Bio: Wouter Alink studied computer science at Twente University, and did his MSc research at the Centrum Wiskunde & Informatica (CWI) and the Netherlands Forensic Institute (NFI). He developed a novel approach towards managing and querying forensic traces extracted from digital evidence. This has led to a nowadays widely used tool within Dutch police for forensic analysis providing forensic investigators with a rich query environment over heterogeneous sources. In 2010, Alink co-founded Spinque, a spin-off of CWI, focusing on DB and IR integration.

=====================================================================

Julia Kiseleva - Optimizing Interactive Systems with Data-Driven Objectives

Effective optimization is essential for interactive systems to provide a satisfactory user experience. However, it is often challenging to find an objective to optimize for. Generally, such objectives are manually crafted and rarely capture complex user needs accurately. Conversely, we propose an approach that infers the objective directly from observed user interactions. These inferences can be made regardless of prior knowledge and across different types of user behavior. We introduce Interactive System Optimizer, a novel algorithm that uses these inferred objectives for optimization. Our main contribution is a new general principled approach to optimizing interactive systems using data-driven objectives.

Bio: Julia Kiseleva is a postdoctoral researcher at the University of Amsterdam at Information and Language Processing Systems Group (ILPS). She defended her PhD thesis titled "Using Contextual Information to Understand Searching and Browsing Behaviour" at the Eindhoven University of Technology in June 2016. The focus of Julia’s research is understanding and predicting user satisfaction with various types of interactive systems. Julia has extensive industrial experience at leading IT companies including Microsoft Research, Microsoft Bing, Yandex.ru, Hewlett Packard Research, E-bay, and Booking.com.