Going-Deeper-with-Convolutional-Neural-Network-for-Stock-Market-Prediction icon indicating copy to clipboard operation
Going-Deeper-with-Convolutional-Neural-Network-for-Stock-Market-Prediction copied to clipboard

Published 20 hours ago • verified publisher icon rosdyana

RandomForest Classifier results

Open Mirmix opened this issue 5 years ago • 3 comments

Thanks for making this work open-source. I have tried to replicate your results using Taiwanese datasets. I have generated images with dimension size of 50 and a period size of 20. I have done testing with a random forest classifier. I have tried a different number of estimators to check the improvement of the result. I get accuracy around 0.55 with the shared Taiwanese dataset. I would like to know whether you have a guess about what I could be missing? I would like to know also why there is such a big gap between my results using the exact same pipeline and the results mentioned in the paper.

Mirmix avatar Dec 19 '19 13:12 Mirmix

Thanks for making this work open-source. I have tried to replicate your results using Taiwanese datasets. I have generated images with dimension size of 50 and a period size of 20. I have done testing with a random forest classifier. I have tried a different number of estimators to check the improvement of the result. I get accuracy around 0.55 with the shared Taiwanese dataset. I would like to know whether you have a guess about what I could be missing? I would like to know also why there is such a big gap between my results using the exact same pipeline and the results mentioned in the paper.

Hi, I got a problem just the same. The accuracy result calculated by deepCNN is also aound 0.55. Do you got the key to increase the accuracy result? Thank you very much.

nkchem09 avatar Jan 25 '21 06:01 nkchem09

Thanks for making this work open-source. I've tried different models on the dataset but the accuracy is just overfitting by choosing all up/down. I would like to know whether you have a guess about what I could be missing?

yc-wang00 avatar Mar 17 '22 21:03 yc-wang00

Thanks for making this work open-source. I have tried to replicate your results using Taiwanese datasets. I have generated images with dimension size of 50 and a period size of 20. I have done testing with a random forest classifier. I have tried a different number of estimators to check the improvement of the result. I get accuracy around 0.55 with the shared Taiwanese dataset. I would like to know whether you have a guess about what I could be missing? I would like to know also why there is such a big gap between my results using the exact same pipeline and the results mentioned in the paper.

I got the same issue here. Have you resolved the issue?

yc-wang00 avatar Mar 17 '22 21:03 yc-wang00