Skip to content

Controllable Generation of Realistic Financial Time Series via Diffusion Models

Notifications You must be signed in to change notification settings

RageAgainstTheAssembly/BacktestingDiffusion

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 

Repository files navigation

BacktestingDiffusion

Controllable Generation of Realistic Financial Time Series via Diffusion Models

Datasets

To run the code, you'll need to download the following financial datasets and place them in the data folder:

  1. S&P 500 Dataset

    • Description: Multivariate daily log returns for S&P 500 constituents
    • Download: S&P 500 Data
  2. MOEX Dataset

    • Description: Multivariate daily log returns for Moscow Exchange stocks
    • Download: MOEX Data
  3. Forex Dataset

    • Description: Multivariate daily exchange rates for major currency pairs
    • Download: Forex Data

Data Setup Instructions

  1. Create a data folder in the root directory of the project if it doesn't exist:
mkdir data
  1. Download all datasets from the provided Google Drive links

  2. Place the downloaded files directly in the data folder without modifying their names

  3. Verify that your data folder structure looks like this:

data/
├── sp500_returns.csv
├── moex_returns.csv
└── forex.csv

About

Controllable Generation of Realistic Financial Time Series via Diffusion Models

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published