This is a CMU school project, where we try applying diffusion models on discontinuous time series data. The data we are operating on is from the Optiver - Trading at the Close Kaggle competition.
Please download the data from this Kaggle dataset: https://www.kaggle.com/datasets/ravi20076/optiver-memoryreduceddatasets/data and place it in the data_raw folder before running the code.
The data processing code and our exploratory data analysis (EDA) can be found in eda.ipynb, please run this notebook before running main.ipynb.
The code for all our models can be found in main.ipynb, just run the notebook sequentially and it should give you the same outputs.