There seems to be a mistake here!

rosdyana / Going-Deeper-with-Convolutional-Neural-Network-for-Stock-Market-Prediction

Repository for Going Deeper with Convolutional Neural Network for Stock Market Prediction

Apache License 2.0

128 stars 69 forks source link

There seems to be a mistake here! #8

Open PenaBrasil opened 1 year ago

PenaBrasil commented 1 year ago

I have been developing and testing models for the financial market for some time. An accuracy of more than 90% seems impossible to me for such simple graphic samples (with little data). I replicated your model and got to 53%. By the way, the same thing was described in the "RandomForest Classifier results" issue. I began to doubt the results of this work. Can you explain these results?

MasterBeard commented 3 months ago

I also took the time to read their article because I noticed it had a lot of citations on Google Scholar. However, I saw that their article included a comparison result with Patel. Having read Patel's article published in Expert System, I know that their study does not divide the training and testing sets according to the time series. So, when I saw this comparison, I was puzzled. How can a model that divides data according to the time sequence be compared with one that does not?