Domain Specific Concept Drift Detectors for Predicting Financial Time Series

TL;DR

This paper evaluates how concept drift detectors perform on financial time series, showing they can improve runtime, are computationally efficient, and can be directly applied to raw data, with new tailored detectors introduced.

Contribution

It introduces three simple, effective concept drift detectors specifically designed for financial time series, demonstrating comparable performance to advanced methods.

Findings

Detectors improve runtime over continuous learning

Detectors are computationally lightweight

Two new tailored detectors perform well on financial data

Abstract

Concept drift detectors allow learning systems to maintain good accuracy on non-stationary data streams. Financial time series are an instance of non-stationary data streams whose concept drifts (market phases) are so important to affect investment decisions worldwide. This paper studies how concept drift detectors behave when applied to financial time series. General results are: a) concept drift detectors usually improve the runtime over continuous learning, b) their computational cost is usually a fraction of the learning and prediction steps of even basic learners, c) it is important to study concept drift detectors in combination with the learning systems they will operate with, and d) concept drift detectors can be directly applied to the time series of raw financial data and not only to the model's accuracy one. Moreover, the study introduces three simple concept drift detectors, tailored to financial time series, and shows that two of them can be at least as effective as the most sophisticated ones from the state of the art when applied to financial time series. Currently submitted to Pattern Recognition