Premium
Online detection of financial time series peaks and troughs: A probability‐based approach *
Author(s) -
Bramante Riccardo,
Facchinetti Silvia,
Zappa Diego
Publication year - 2019
Publication title -
statistical analysis and data mining: the asa data science journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.381
H-Index - 33
eISSN - 1932-1872
pISSN - 1932-1864
DOI - 10.1002/sam.11411
Subject(s) - computer science , volatility (finance) , strengths and weaknesses , econometrics , crossover , time series , identification (biology) , data mining , sample (material) , series (stratigraphy) , artificial intelligence , machine learning , mathematics , paleontology , philosophy , chemistry , botany , epistemology , chromatography , biology
The problem related to the identification of a change in time series trajectories plays a crucial role in many contexts. In this paper, we propose a flexible and computationally efficient procedure for turning point identification based on hypothesis testing applied to the difference between two consecutive slopes in a rolling regression framework. Along with the description of the methodology, to measure the performance of the method we have applied it to the S&P 500 Stock Index and its subsector indices. By using an in‐sample/out‐of‐sample approach we compare results with the profit/losses we could obtain by using the moving average crossover strategy. Results show that the operating signals obtained by our proposal may better enable financial analysts to make profitable decisions. Finally we present an extensive simulation study to show the weaknesses and strengths of the proposal under different expected returns and volatility scenarios.