A significant number of learning problems involve the accurate classification of rare events or outliers from time series data. For example, the detection of a flash crash or rogue trading from financial markets data, or heart arrhythmia from an electrocardiogram. Due to the rarity of these events, machine learning classifiers for detecting these events may be biased towards avoiding false positives because any potential for false positives is greatly exaggerated by the number of negative samples in the data set. This project will focus on the improvement of the imbalance time series classification algorithm based on structure preserving oversampling, and the implementation of it to a stable R package. The algorithm will be tested with various learning algorithms undersampling techniques. And the R package will be tested with the real world dataset.




  • Brian Peterson
  • Diego Klabjan
  • Matthew Dixon