Data stream classification with concept drift and verification latency

Author(s)

Denis Moreira dos Reis

• Document type: Master's Dissertation
• Press: São Carlos.
• Institution: Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB)
• Defense date: 2016-09-27

Examining board members

Gustavo Enrique de Almeida Prado Alves Batista; Robson Leonardo Ferreira Cordeiro; Ricardo Bastos Cavalcante Prudêncio; Marcela Xavier Ribeiro

• Advisor: Gustavo Enrique de Almeida Prado Alves Batista

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 distribution changes over time, causing what is known as concept drift. 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 drifts. However, most of them assume that, once the classification algorithm labels an event, its actual label become readily available. This work explores the complementary situations, with a review of the most important published works and an analysis over the impact of delayed true labeling, including no true label availability at all. Furthermore, this work proposes a new algorithm that heavily reduces the complexity of applying Kolmogorov- Smirnov non-parametric hypotheis test, turning it into an uselful tool for analysis on data streams. As an instantiation of its usefulness, we present an unsupervised drift-detection method that, along with Active Learning and Transfer Learning approaches, decreases the number of true labels that are required to keep good classification performance over time, even in the presence of concept drifts. (AU)

• FAPESP's process: 14/12333-7 - Data stream classification with concept drift and extreme verification latency
• Grantee: Denis Moreira dos Reis
• Support Opportunities: Scholarships in Brazil - Master