TensorFlow 2.0 Tutorial for Beginners 11 - Bank Customer Satisfaction Prediction Using CNN

Поділитися
Вставка
  • Опубліковано 24 гру 2024

КОМЕНТАРІ • 23

  • @nadeemroshan341
    @nadeemroshan341 4 роки тому +2

    Your model is just predicting 0's. In the test set exactly 96.05% of the targets are 0's, this explains why you're getting 96.05% accuracy. The actual metric used in the kaggle leaderboard is Area under ROC not '1-error_rate'. Your Area under ROC score would be 0.5. Try oversampling to balance the test data before feeding it to the CNN

  • @shaikrasool1316
    @shaikrasool1316 4 роки тому +3

    Iam a beginner,
    Cnn is used for image classification...
    Here we doing on numerical data.
    When to use conv1D and conv2D

    • @sabkabaaphu
      @sabkabaaphu 4 роки тому +2

      1d for datasets and 2d for images

  • @muhammadzubairbaloch3224
    @muhammadzubairbaloch3224 5 років тому +1

    please make vides image dateset preprocessing that are not publically available. Thanks

    • @KGPTalkie
      @KGPTalkie  5 років тому

      Yeah sure. I will try to do it.

  • @sabkabaaphu
    @sabkabaaphu 4 роки тому +1

    This model is not working for kaggle. There is need to do advance feature engineering. Getting only 50% accuracy

  • @redhotchilipeppers38
    @redhotchilipeppers38 4 роки тому

    Hey! Great videos first and foremost. I modified the model slightly (has 95.6% train and test acc) but when I make predictions on the actual test data on Kaggle and submit for scoring, the score received is 0.46723. Why is there such a large discrepancy? What is the reason?

    • @KGPTalkie
      @KGPTalkie  4 роки тому

      Try to use balance and unbalance both. And see how it is performing.

    • @redhotchilipeppers38
      @redhotchilipeppers38 4 роки тому

      @@KGPTalkie after noticing some issues in my predictions, I revised the code to achieve the correct accuracy of 0.65773.
      The reason for the discrepancy is because the evaluation of the model on Kaggle is the "area under the ROC curve". Since our training data is around 96% satisfied customers. The model is naive and simply predicts all customers are satisfied, thus obtaining ~96% accuracy.
      I'm working now to try and fix this issue with a combination of 1) under sampling the satisfied customer pool 2) modifying the loss function to more harshly penalize classifying a dissatisfied customer as satisfied.
      Any other tips?

    • @vinojose271
      @vinojose271 4 роки тому

      @@redhotchilipeppers38 Please let us know if are getting better results. Also if possible, please share us the code.

  • @raymourradhakrishnan5709
    @raymourradhakrishnan5709 5 років тому

    @LAXMI KANT Hi, Sir, Thank you for making this video. I have been having an issue, as I wanted to test out the model that I have built. I am using a new CSV file, with data (8 inputs) and am trying to pass it through the model.predict() function... BUT i keep getting this error "ValueError: Error when checking input: expected conv1d_input to have 3 dimensions, but got array with shape (8, 1)" ---- I have tried to reshape the data but have been unsuccessful. Any help would be greatly appreciated.

    • @KGPTalkie
      @KGPTalkie  5 років тому +1

      You need to reshape the data.. Follow exact procedure for testing data as you did for training data.

  • @mahdiheidarpoor9452
    @mahdiheidarpoor9452 5 років тому +1

    Its really interesting video, but you must use train and test data sets in the library, but you use only the train set and split train set to train and test...
    anyway, your videos are perfect!

    • @KGPTalkie
      @KGPTalkie  5 років тому +1

      Thank you for the watching ❤️. We do not have label for test set so can't test the accuracy therefore I had splitted train set in train and test set.

  • @MaziyarPanahi
    @MaziyarPanahi 5 років тому +1

    Awesome video! It would be great if you can also download the test from Kaggle and show how to evaluate the model by that dataset and how to prepare it for submission.
    Great work, thanks again.

    • @KGPTalkie
      @KGPTalkie  5 років тому

      Thank you so much for watching ❤️ 😍

  • @muhammadzubairbaloch3224
    @muhammadzubairbaloch3224 5 років тому +1

    please sir make the videos on medical image analysis

    • @KGPTalkie
      @KGPTalkie  5 років тому

      Thank you for your feedback. I was also thinking the same. Please stay tuned for more videos. Thanks for watching.

  • @myonlineschool4759
    @myonlineschool4759 5 років тому

    When I fit the model, I got this error "AttributeError: 'function' object has no attribute 'shape'" >>>history=model.fit(X_train,y_train,epochs=epochs,validation_data=(X_test,y_test),verbose=1)

    • @KGPTalkie
      @KGPTalkie  5 років тому

      Please compare with original file. Link is given in the video description.

    • @myonlineschool4759
      @myonlineschool4759 5 років тому

      @@KGPTalkie Thank you for your reply. I have already solve this issue. Your lecture is really amazing.

  • @taylormcclenny1416
    @taylormcclenny1416 5 років тому

    Thank you!