Visual Time Series Forecasting: An Image-driven Approach
This work introduces a new paradigm for time series forecasting by incorporating vision-based approaches, which could benefit practitioners who rely on visualizations to reason about forecasts.
This paper proposes a novel framework for time series forecasting that uses an image-driven approach, capturing input data as an image and training a model to produce subsequent images, thereby predicting distributions rather than pointwise values. The visual forecasting method is shown to be effective for cyclic data and outperforms numerical baselines like ARIMA on image-based evaluation metrics.
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.