Towards Dynamic Trend Filtering through Trend Point Detection with Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based method for dynamic trend filtering that detects essential trend points, effectively capturing abrupt changes in time series data and improving forecasting accuracy.

Contribution

It proposes a novel RL-based approach to identify dynamic trend points, enabling adaptive filtering that preserves abrupt changes unlike traditional methods.

Findings

Outperforms existing trend filtering algorithms in capturing abrupt changes.

Enhances forecasting accuracy by preserving critical trend points.

Demonstrates flexibility in noise filtering and trend detection.

Abstract

Trend filtering simplifies complex time series data by applying smoothness to filter out noise while emphasizing proximity to the original data. However, existing trend filtering methods fail to reflect abrupt changes in the trend due to `approximateness,' resulting in constant smoothness. This approximateness uniformly filters out the tail distribution of time series data, characterized by extreme values, including both abrupt changes and noise. In this paper, we propose Trend Point Detection formulated as a Markov Decision Process (MDP), a novel approach to identifying essential points that should be reflected in the trend, departing from approximations. We term these essential points as Dynamic Trend Points (DTPs) and extract trends by interpolating them. To identify DTPs, we utilize Reinforcement Learning (RL) within a discrete action space and a forecasting sum-of-squares loss function as a reward, referred to as the Dynamic Trend Filtering network (DTF-net). DTF-net integrates flexible noise filtering, preserving critical original subsequences while removing noise as required for other subsequences. We demonstrate that DTF-net excels at capturing abrupt changes compared to other trend filtering algorithms and enhances forecasting performance, as abrupt changes are predicted rather than smoothed out.