I
Ioannis Katakis
Researcher at National and Kapodistrian University of Athens
Publications - 51
Citations - 6155
Ioannis Katakis is an academic researcher from National and Kapodistrian University of Athens. The author has contributed to research in topics: Sentiment analysis & Voting. The author has an hindex of 17, co-authored 49 publications receiving 5465 citations. Previous affiliations of Ioannis Katakis include Aristotle University of Thessaloniki & University of Cyprus.
Papers
More filters
Journal ArticleDOI
A Multi-Factor Analysis of Forecasting Methods: A Study on the M4 Competition
TL;DR: The main goal of this study is to recognize the key elements of the contemporary forecasting methods, reveal what made them excel in the M4 competition, and eventually provide insights towards better understanding the forecasting task.
Journal ArticleDOI
Special Issue on “Solving complex machine learning problems with ensemble methods”
TL;DR: The main goal of this special issue is to spread the knowledge about ensemble strategies that not only focus on supervised classification, but can also be used to solve difficult and general machine learning problems related to different fields of expertise.
Proceedings ArticleDOI
Mining hidden constrained streams in practice: informed search in dynamic filter spaces
Nikolaos Panagiotou,Ioannis Katakis,Dimitrios Gunopulos,Vana Kalogeraki,Elizabeth M. Daly,Jia Yuan Yu,Brendan O Brien +6 more
TL;DR: This work introduces a search approach on a dynamic filter space using heterogeneous filters (not only keywords) making no assumptions about the attributes of the individual filters and demonstrates the effectiveness of the approaches on a set of topics of static and dynamic nature.
Proceedings ArticleDOI
REMI, Reusable Elements for Multi-Level Information Availability: Demo
Avigdor Gal,Nicolo Rivetti,Arik Senderovich,Dimitrios Gunopulos,Ioannis Katakis,Nikolaos Panagiotou,Vana Kalogeraki +6 more
TL;DR: REMI, a reusable elements framework to handle varying degrees of information availability by design from two complementary angles, namely graceful degradation (GRADE) and data enrichment (DARE) is presented.