Visual Time Series Forecasting: An Image-driven Approach

Time series forecasting is essential for agents to make decisions. Traditional approaches rely on statistical methods to forecast given past numeric values. In practice, end-users often rely on visualizations such as charts and plots to reason about their forecasts. Inspired by practitioners, we re-imagine the topic by creating a novel framework to produce visual forecasts, similar to the way humans intuitively do. In this work, we leverage advances in deep learning to extend the field of time series forecasting to a visual setting. 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. We examine various synthetic and real datasets with diverse degrees of complexity. Our experiments show that visual forecasting is effective for cyclic data but somewhat less for irregular data such as stock price. Importantly, when using image-based evaluation metrics, we find the proposed visual forecasting method to outperform various numerical baselines, including ARIMA and a numerical variation of our method. We demonstrate the benefits of incorporating vision-based approaches in forecasting tasks – both for the quality of the forecasts produced, as well as the metrics that can be used to evaluate them.

💡 Research Summary

The paper “Visual Time Series Forecasting: An Image‑driven Approach” introduces a novel framework that recasts the classic numeric time‑series forecasting problem as an image‑to‑image regression task. Instead of feeding raw numerical values into statistical or neural models, the authors first plot each 80‑point series as a 80 × 80 grayscale image. Pixels are scaled to the