Dear Abdur,

A perfect MSE is highly suspicious. This implies that the model is being trained and tested on the same data. Instead, k-fold cross validation should be employed.

https://machinelearningmastery.com/k-fold-cross-validation/

Also, it is possible that the output is a deterministic function of the input. For instance, if the input is dollars and output is euros. The fixed ratio has no variance, and thus no MSE.

Nathan Zavanelli Thank you very much for the response. Although I’ve utilized different data for both training and testing, but I will employ K-fold Validation.

Thanks for the guidance

Dear Abdur Rasheed

As others mentioned, it is possible. It is better to check your input and target data.

Kindly check these links:

https://stackoverflow.com/questions/59375220/how-to-get-the-mse-of-the-node-in-the-decisiontreeregressor-of-scikit-learn

https://datascience.stackexchange.com/questions/84427/how-to-explain-mae-mse-at-each-node-of-decision-tree-for-regression-in-sklearn-p