Saved in:
Bibliographic Details
Main Authors: Horvatic, Davor, Baric, Domjan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.04339
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913666421489664
author Horvatic, Davor
Baric, Domjan
author_facet Horvatic, Davor
Baric, Domjan
contents We introduce an interpretable deep learning model for multivariate time series forecasting that prioritizes both predictive performance and interpretability - key requirements for understanding complex physical phenomena. Our model not only matches but often surpasses existing interpretability methods, achieving this without compromising accuracy. Through extensive experiments, we demonstrate its ability to identify the most relevant time series and lags that contribute to forecasting future values, providing intuitive and transparent explanations for its predictions. To minimize the need for manual supervision, the model is designed so one can robustly determine the optimal window size that captures all necessary interactions within the smallest possible time frame. Additionally, it effectively identifies the optimal model order, balancing complexity when incorporating higher-order terms. These advancements hold significant implications for modeling and understanding dynamic systems, making the model a valuable tool for applied and computational physicists.
format Preprint
id arxiv_https___arxiv_org_abs_2501_04339
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DCIts -- Deep Convolutional Interpreter for time series
Horvatic, Davor
Baric, Domjan
Machine Learning
Applied Physics
We introduce an interpretable deep learning model for multivariate time series forecasting that prioritizes both predictive performance and interpretability - key requirements for understanding complex physical phenomena. Our model not only matches but often surpasses existing interpretability methods, achieving this without compromising accuracy. Through extensive experiments, we demonstrate its ability to identify the most relevant time series and lags that contribute to forecasting future values, providing intuitive and transparent explanations for its predictions. To minimize the need for manual supervision, the model is designed so one can robustly determine the optimal window size that captures all necessary interactions within the smallest possible time frame. Additionally, it effectively identifies the optimal model order, balancing complexity when incorporating higher-order terms. These advancements hold significant implications for modeling and understanding dynamic systems, making the model a valuable tool for applied and computational physicists.
title DCIts -- Deep Convolutional Interpreter for time series
topic Machine Learning
Applied Physics
url https://arxiv.org/abs/2501.04339