Context Matters: Leveraging Contextual Features for Time Series Forecasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912187138703360 |
|---|---|
| author | Chattopadhyay, Sameep Paliwal, Pulkit Narasimhan, Sai Shankar Agarwal, Shubhankar Chinchali, Sandeep P. |
| author_facet | Chattopadhyay, Sameep Paliwal, Pulkit Narasimhan, Sai Shankar Agarwal, Shubhankar Chinchali, Sandeep P. |
| contents | Time series forecasts are often influenced by exogenous contextual features in addition to their corresponding history. For example, in financial settings, it is hard to accurately predict a stock price without considering public sentiments and policy decisions in the form of news articles, tweets, etc. Though this is common knowledge, the current state-of-the-art (SOTA) forecasting models fail to incorporate such contextual information, owing to its heterogeneity and multimodal nature. To address this, we introduce ContextFormer, a novel plug-and-play method to surgically integrate multimodal contextual information into existing pre-trained forecasting models. ContextFormer effectively distills forecast-specific information from rich multimodal contexts, including categorical, continuous, time-varying, and even textual information, to significantly enhance the performance of existing base forecasters. ContextFormer outperforms SOTA forecasting models by up to 30% on a range of real-world datasets spanning energy, traffic, environmental, and financial domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_12672 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Context Matters: Leveraging Contextual Features for Time Series Forecasting Chattopadhyay, Sameep Paliwal, Pulkit Narasimhan, Sai Shankar Agarwal, Shubhankar Chinchali, Sandeep P. Machine Learning Artificial Intelligence Time series forecasts are often influenced by exogenous contextual features in addition to their corresponding history. For example, in financial settings, it is hard to accurately predict a stock price without considering public sentiments and policy decisions in the form of news articles, tweets, etc. Though this is common knowledge, the current state-of-the-art (SOTA) forecasting models fail to incorporate such contextual information, owing to its heterogeneity and multimodal nature. To address this, we introduce ContextFormer, a novel plug-and-play method to surgically integrate multimodal contextual information into existing pre-trained forecasting models. ContextFormer effectively distills forecast-specific information from rich multimodal contexts, including categorical, continuous, time-varying, and even textual information, to significantly enhance the performance of existing base forecasters. ContextFormer outperforms SOTA forecasting models by up to 30% on a range of real-world datasets spanning energy, traffic, environmental, and financial domains. |
| title | Context Matters: Leveraging Contextual Features for Time Series Forecasting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.12672 |