This repository is the reporisity of Prompt-Based Time Series Forecasting: A New Task and Dataset (currently under submission). PISA is a large-scale dataset including three real-world forecasting scenarios (three sub-sets) with 311,932 data instances in total. It is designed to support and facilitate the novel PromptCast task proposed in the paper.

2022/06/10 This repo is open for review.

Exisiting numerical-based forecasting VS. Prompt-based forecasting

• RMSE
• MAE
• Missing Rate: whether the numerical forecasting target can be decoded (via string parsing) from the generated output prompts.

The proposed PISA dataset contrains three real-world forecasting scenarios:

• CT: city temperature forecasting
• ECL: electricity consumption forecasting
• SG: humana mobility visitor flow forecasting

Details of three sub-sets

Dataset
|── PISA-Prompt
    │── CT
        │-- train_x_prompt.txt
        │-- train_y_prompt.txt
        │-- val_x_prompt.txt
        │-- val_y_prompt.txt
        │-- test_x_prompt.txt
        │-- test_y_prompt.txt
    │── ECL
        │-- train_x_prompt.txt
        │-- train_y_prompt.txt
        │-- val_x_prompt.txt
        │-- val_y_prompt.txt
        │-- test_x_prompt.txt
        │-- test_y_prompt.txt  
    │── SG
        │-- train_x_prompt.txt
        │-- train_y_prompt.txt
        │-- val_x_prompt.txt
        │-- val_y_prompt.txt
        │-- test_x_prompt.txt
        │-- test_y_prompt.txt   

Please check Benchmark folder for the implementations of benchmarked methods.

RMSE and MAE performance

Missing Rate results

Results under train-from-scratch and cross-scenario zero-shot settings

• GitHub repo open for reviewing
• Paper release
• Full dataset release in this repo
• Full dataset release in HuggingFace Dataset page
• Leaderboard Website Launch
• ...
• ...