Srijan Sood, Zhen Zeng, Naftali Cohen, Tucker Balch, Manuela Veloso
arXiv 18 Nov 2020 · cs.CV
arXiv:2011.09052 · PDF · DOI · OpenAlex · Extracted main text
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.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio (2016) Deep learning | 0.644 | 2 | 2 | 100% |
| 2 | Lasse Heje Pedersen (2019) Efficiently inefficient: how smart money invests and market prices are determined | 0.644 | 2 | 2 | 100% |
| 3 | Jerome Friedman, Trevor Hastie, and Robert Tibshirani (2001) The elements of statistical learning | 0.585 | 3 | 1 | 100% |
| 4 | David Byrd (2019) Explaining agent-based financial market simulation | 0.511 | 2 | 1 | 100% |
| 5 | Rob J Hyndman and George Athanasopoulos (2018) Forecasting: principles and practice | 0.511 | 2 | 1 | 100% |
| 6 | Spyros Makridakis and Michele Hibon (2000) The M3-Competition: results, conclusions and implications | 0.511 | 2 | 1 | 100% |
| 7 | Pinar Akyazi and Touradj Ebrahimi (2019) Learning-Based Image Compression using Convolutional Autoencoder and Wavelet Decomposition. In Proceedings of the IEEE/CVF Confe… | 0.405 | 1 | 1 | 100% |
| 8 | Abubakar Abid and James Y Zou (2018) Learning a warping distance from unlabeled time series using sequence autoencoders. In Advances in Neural Information Processing… | 0.405 | 1 | 1 | 100% |
| 9 | Guillaume Alain and Yoshua Bengio (2014) What regularized auto-encoders learn from the data-generating distribution | 0.405 | 1 | 1 | 100% |
| 10 | Wei Bao, Jun Yue, and Yulei Rao (2017) A deep learning framework for financial time series using stacked autoencoders and long-short term memory | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 37 scored citations.