A fully automated periodicity detection in time series

Tom Puech, Matthieu Boussard

Abstract: This paper presents a method to autonomously find periodicities in a signal. It is based on the same idea of using Fourier Transform and autocorrelation function presented in Vlachos et al. 2005. While showing interesting results this method does not perform well on noisy signals or signals with multiple periodicities. Thus, our method adds several new extra steps (hints clustering, filtering and detrending) to fix these issues. Experimental results show that the proposed method outperforms the state of the art algorithms.

Keywords: Time series, feature engineering, period detection, machine learning

TL;DR: This paper presents a method to autonomously find multiple periodicities in a signal, using FFT and ACF and add three news steps (clustering/filtering/detrending)