TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting

TL;DR

TSNN is a non-parametric, interpretable framework for traffic time series forecasting that leverages memory matching and periodicity, achieving competitive results without trainable parameters.

Contribution

The paper introduces TSNN, a novel non-parametric, interpretable model for traffic forecasting that operates without trainable parameters and utilizes memory matching.

Findings

TSNN achieves competitive performance on real-world datasets.

The model effectively visualizes the decoupling process.

It demonstrates interpretability and contribution analysis of time steps.

Abstract

Although many complex models were proposed to analyze time series data, some studies have demonstrated remarkable performance with simpler structures. A recent study proposed a non-parametric framework for 3D point cloud classification, which has the potential to be adapted for time series forecasting and enable interpretability. Inspired by the previous works, we present TSNN, a non-parametric and interpretable framework for traffic time series forecasting. TSNN consists of multiple layers that decouple the time series by matching the entries in a memory bank, where the memory bank is constructed using a similar matching process within the training set. It leverages the periodicity in traffic data to enhance forecasting accuracy while maintaining a simple model architecture. The proposed model operates without trainable parameters, preserving its inherent interpretability. In the experiments, TSNN achieves competitive performance compared to the typical deep learning models in four real-world traffic flow datasets. We also visualize the decoupling process to show the effectiveness of the components. Finally, we demonstrate the interpretability of the model and illustrate the contribution of each time step within the memory bank.