Discussing the article: "Data label for time series mining (Part 4)：Interpretability Decomposition Using Label Data"
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Check out the new article: Data label for time series mining (Part 4)：Interpretability Decomposition Using Label Data.
This series of articles introduces several time series labeling methods, which can create data that meets most artificial intelligence models, and targeted data labeling according to needs can make the trained artificial intelligence model more in line with the expected design, improve the accuracy of our model, and even help the model make a qualitative leap!
In the previous article of this series, we mentioned the NHITS model, where we only validated the prediction of closing prices for a single variable input. In this article, we will discuss the Interpretability of the model and about using multiple covariates to predict closing prices. we will use a different model, NBEATS, for demonstration, to provide more possibilities. However, it should be noted that the focus of this article should be on the Interpretability of the model, and the answer to why the topic of covariates is also introduced will be given. So that you can use different models to verify your ideas at any time. Of course, these two models are essentially high-quality interpretable models, and you can also extend to other models to verify your ideas with the libraries mentioned in my article. It is worth mentioning that this series of articles aims to provide solutions to problems, please consider carefully before directly applying it to your real trading, the real trading implementation may require more parameter adjustments and more optimization methods to provide reliable and stable results.
Author: Yuqiang Pan