Data stream classification with concept drift and extreme verification latency

• Grant number: 14/12333-7
• Support Opportunities: Scholarships in Brazil - Master
• Start date: September 01, 2014
• End date: July 31, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Agreement: Coordination of Improvement of Higher Education Personnel (CAPES)
• Principal Investigator: Gustavo Enrique de Almeida Prado Alves Batista
• Grantee: Denis Moreira dos Reis
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated scholarship(s): 15/01701-8 - Data stream analysis and evaluation under the presence of verification latency, BE.EP.MS

Abstract

Despite the relatively maturity of batch-mode supervised learning research, in which the data typifies stationary problems, many real world applications deal with data streams whose statistical properties change over time, causing what is known as concept drift. For such applications a large body of research has been done in the last years, with the objective of creating new models that are accurate even in the presence of concept drift. However, most of them assume that, once the classifier algorithm labels an event, its actual label become available. This project researches and shows solutions belonging to a new paradigm, where the unlabeled data is drifted back to its originally learned distribution. Such new paradigm allows an effective use of machine learning in the presence of concept drift, even when the actual labels are never available, keeping high performance both in accuracy and computational cost. Partial results serve as evidence of the viability of this paradigm. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

DOS REIS, DENIS; FLACH, PETER; MATWIN, STAN; BATISTA, GUSTAVO; ASSOC COMP MACHINERY. Fast Unsupervised Online Drift Detection Using Incremental Kolmogorov-Smirnov Test. KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, v. N/A, p. 10-pg., 2016-01-01. (15/01701-8, 13/50379-6, 14/12333-7)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

REIS, Denis Moreira dos. Data stream classification with concept drift and verification latency. 2016. Master's Dissertation - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.