Visual Time Series Forecasting: An Image-driven Approach

2021/07/02 by Naftali Cohen, Srijan Sood, Cohen, Naftali +7
Decision Sciences · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Economics and business #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Statistical Finance (q-fin.ST) #Stock Market Forecasting Methods #Trading and Market Microstructure (q-fin.TR)

paper · pdf · doi:10.48550/arxiv.2107.01273

openalex publication_date 2021/07/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this work, we address time-series forecasting as a computer vision task. We capture input data as an image and train a model to produce the subsequent image. This approach results in predicting distributions as opposed to pointwise values. To assess the robustness and quality of our approach, we examine various datasets and multiple evaluation metrics. Our experiments show that our forecasting tool is effective for cyclic data but somewhat less for irregular data such as stock prices. Importantly, when using image-based evaluation metrics, we find our method to outperform various baselines, including ARIMA, and a numerical variation of our deep learning approach.

Related

• From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting
• Forecasting with Deep Learning
• Your time series is worth a binary image: machine vision assisted deep framework for time series forecasting
• VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
• Deep Video Prediction for Time Series Forecasting