search

cosimoizzo / DDFM

Deep Dynamic Factor Models
MIT License
13 stars 6 forks source link

Request for Source Code: "Encoding the US Economy in Real Time" - Deep Dynamic Factor Models #1

Open Arminkhayati opened 11 months ago

Arminkhayati commented 11 months ago

Dear Cosimo

I hope this message finds you well. I am writing to express my fascination with your work on "Deep Dynamic Factor Models" and its application in "Encoding the US Economy in Real Time." Your research has been an inspiration to my own work on mixed frequency data nowcasting.

As I delve into implementing and studying dynamic factor models for nowcasting, I believe that your code for "Encoding the US Economy in Real Time" would be immensely valuable in understanding the practical aspects of your approach. It would greatly aid my efforts in applying these techniques to my own research.

I kindly request access to the source code related to "Encoding the US Economy in Real Time" from your repository. If there are any specific terms or conditions under which you share your code, please let me know, and I assure you that I will comply with them accordingly.

Furthermore, I would like to express my intention to reference your work in my own research on mixed frequency data nowcasting. Proper attribution and recognition of your contributions are essential, and I will ensure to cite your paper appropriately in any related work I publish.

Thank you for your time and consideration. I look forward to your response and the opportunity to learn from your valuable research.

cosimoizzo commented 10 months ago

Thank you so much for your interest. In the repository you can find the code replicating the simulation results of the paper. The code can be adapted to your data and different frequencies. The paper is now under review and we plan to update the code with the application to real data at a second stage and once the process is finished. Please feel free to write to us if you have any other question.

Arminkhayati commented 10 months ago

Thank you so much for your interest. In the repository you can find the code replicating the simulation results of the paper. The code can be adapted to your data and different frequencies. The paper is now under review and we plan to update the code with the application to real data at a second stage and once the process is finished. Please feel free to write to us if you have any other question.

Thank you very much for your quick response. Could you please give me some hints on how to prepare and test your model for a mixed frequency data forecasting with minutely input time series and hourly target data? I will appreciate your help.