Nearest-neighbor-based approach to time-series classification

• Published in: Decision Support Systems Vol. 53; no. 1; pp. 207 - 217
• Main Authors: Lee, Yen-Hsien, Wei, Chih-Ping, Cheng, Tsang-Hsiang, Yang, Ching-Ting
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.04.2012; Elsevier; Elsevier Sequoia S.A
• Subjects: Applied sciences; Churn prediction; Classification; Classification analysis; Computer science; control theory; systems; Data mining; Data processing. List processing. Character string processing; Decision support systems; Empirical analysis; Exact sciences and technology; False alarms; Firm modelling; Inference from stochastic processes; time series analysis; k Nearest neighbor classification; Mathematical models; Mathematics; Memory organisation. Data processing; Operational research and scientific management; Operational research. Management science; Optimization algorithms; Probability and statistics; Sciences and techniques of general use; Software; Statistics; Studies; Telecommunications data mining; Telecommunications industry; Time series; Time-series classification; Time-series similarity; Training; Transformations; Turnover; Telecommunications data mining; k Nearest neighbor classification; Classification analysis; Time-series similarity; Churn prediction; Data mining; Time-series classification; Mobile radiocommunication; Nearest neighbour; Data analysis; Statistical analysis; Similarity; Volatility; Empirical method; Time series; Telecommunication; Modeling; Information loss; Variance; False alarm rate; Supplier customer relationship; Efficiency; Classification; Time analysis
• ISSN: 0167-9236; 1873-5797
• DOI: 10.1016/j.dss.2011.12.014

Many interesting applications involve predictions based on a time-series sequence or a set of time-series sequences, which are referred to as time-series classification problems. Prior classification analysis research predominately focuses on constructing a classification model from training instances that involve non-time-series attributes. Direct application of traditional classification analysis techniques to time-series classification problems requires the transformation of time-series attributes into non-time-series ones by applying some statistical operations (e.g., average, sum, variance). However, such statistical-transformation-based approach often results in information loss and, in turn, imperils classification effectiveness. In this study, we propose a time-series classification technique based on the k-nearest-neighbor (kNN) classification approach. Using churn prediction of the mobile telecommunications industry as an evaluation application, our empirical evaluation results show that the proposed kNN-based time-series classification (kNN-TSC) technique achieves better performance (measured by miss and false alarm rates) than the statistical-transformation-based approach does. ► We highlight the importance of time-series classification problems. ► We develop the kNN-TSC technique for time-series classification problems. ► We evaluate kNN-TSC using churn prediction as the evaluation application. ► kNN-TSC generally outperforms the benchmark technique in miss and false alarm rates. ► kNN-TSC with the stratified average method is capable of handling imbalanced data sets.