Visual Forecasting of Time Series with Image-to-Image Regression

by   Naftali Cohen, et al.

Time series forecasting is essential for agents to make decisions in many domains. Existing models rely on classical statistical methods to predict future values based on previously observed numerical information. Yet, practitioners often rely on visualizations such as charts and plots to reason about their predictions. Inspired by the end-users, we re-imagine the topic by creating a framework to produce visual forecasts, similar to the way humans intuitively do. In this work, we take a novel approach by leveraging advances in deep learning to extend the field of time series forecasting to a visual setting. We do this by transforming the numerical analysis problem into the computer vision domain. Using visualizations of time series data as input, we train a convolutional autoencoder to produce corresponding visual forecasts. 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, we find the proposed visual forecasting method to outperform numerical baselines. We attribute the success of the visual forecasting approach to the fact that we convert the continuous numerical regression problem into a discrete domain with quantization of the continuous target signal into pixel space.


page 1

page 8


Visual Time Series Forecasting: An Image-driven Approach

In this work, we address time-series forecasting as a computer vision ta...

Hierarchical Time Series Forecasting with Bayesian Modeling

We encounter time series data in many domains such as finance, physics, ...

Forecasting Granular Audience Size for Online Advertising

Orchestration of campaigns for online display advertising requires marke...

Predicting the Future is like Completing a Painting!

This article is an introductory work towards a larger research framework...

Attention-based Domain Adaptation for Time Series Forecasting

Recent years have witnessed deep neural networks gaining increasing popu...

A Framework for Imbalanced Time-series Forecasting

Time-series forecasting plays an important role in many domains. Boosted...

Robust Forecasting for Robotic Control: A Game-Theoretic Approach

Modern robots require accurate forecasts to make optimal decisions in th...

Please sign up or login with your details

Forgot password? Click here to reset