Enhancement of Bank Loan Approval Prediction about dl-simplified HOT 23 CLOSED

Cool. Issue assigned to you @kumar8074

Thank you @abhisheks008

from dl-simplified.

OK got it

from dl-simplified.

Cool go ahead @kumar8074

from dl-simplified.

Hey @abhisheks008 i'm almost done with the project and accuracy is ticking around 95% i know it's slightly lesser than the previous one but the previous model is not actually accuracte because the model has 2 neurons in the output layer but for the binary classification it should be 1 also it uses softmax activation for the output layer but the recommended for binary classification is sigmoid also it uses the categorical_crossentropy as the loss function but the recommended is binary_crossentropy.

However if you want me to improve the evaluation scores more i can do that by hyperparameter tuning which will take couple of more days need to run some more experiments

It's better to increase the accuracy a bit. You can take your time and come up with better solution.

Sure Done 👍

from dl-simplified.

Full name : Vaidehi Shende
GitHub Profile Link : https://github.com/Vaidehi-Shende
Email ID : [email protected]
Approach for this Project : To implement various Deep Learning algorithms including CNNs, RNNs, LSTM
What is your participant role? (Mention the Open Source program): SWOC

from dl-simplified.

Apart from the existing model of this project what are the models you are trying to implement? Can you specify a bit on that.

from dl-simplified.

Enhance the Bank Loan Approval Prediction project by implementing a Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM) and Autoencoders for feature learning after doing Exploratory Data Analysis (EDA), model fitting, hyperparameter tuning, and training/testing, comparing their accuracy scores for optimal model selection.

from dl-simplified.

Assigned to @Vaidehi-Shende under SWOC S4.

from dl-simplified.

Hi @abhisheks008, can you please assign this project to me?

Full name : Lalan Kumar
GitHub Profile Link : https://github.com/kumar8074
Email ID : [email protected]
Approach for this Project : I'll first try to use my own DL algorithms and after that i'll utilize the existing algorithms using transfer learning technique and also i'll try out encoders or GANs to get the best accuracy and the evaluation results.
What is your participant role? GSSoC'24

from dl-simplified.

You need to enhance the existing project and make the changes accordingly with better results. Are you okay with this?
@kumar8074

from dl-simplified.

You need to enhance the existing project and make the changes accordingly with better results. Are you okay with this?
@kumar8074

Yes absolutely @abhisheks008

from dl-simplified.

Cool. Issue assigned to you @kumar8074

from dl-simplified.

Hey @abhisheks008 just had a question, Should I directly complete this project and make a pull request or should i have to show day to day progress? If i have to show day to day progress how to do that ? as i'm quite new to open-source i don't know how to do that can you please help me with that?

from dl-simplified.

Hey @abhisheks008 just had a question, Should I directly complete this project and make a pull request or should i have to show day to day progress? If i have to show day to day progress how to do that ? as i'm quite new to open-source i don't know how to do that can you please help me with that?

Complete your work and then push the code. No need to push a day to day progress. Take your time and come up with the best quality code.

from dl-simplified.

Hey @abhisheks008 can i change the dataset used in this project? the dataset that have been previously used is heavily imbalanced

from dl-simplified.

Hey @abhisheks008 can i change the dataset used in this project? the dataset that have been previously used is heavily imbalanced

Can you share the dataset URL/source you are planning to use here?

from dl-simplified.

https://www.kaggle.com/datasets/architsharma01/loan-approval-prediction-dataset

from dl-simplified.

Hey @abhisheks008 i'm almost done with the project and accuracy is ticking around 95% i know it's slightly lesser than the previous one but the previous model is not actually accuracte because the model has 2 neurons in the output layer but for the binary classification it should be 1 also it uses softmax activation for the output layer but the recommended for binary classification is sigmoid also it uses the categorical_crossentropy as the loss function but the recommended is binary_crossentropy.

However if you want me to improve the evaluation scores more i can do that by hyperparameter tuning which will take couple of more days need to run some more experiments

from dl-simplified.

Hey @abhisheks008 i'm almost done with the project and accuracy is ticking around 95% i know it's slightly lesser than the previous one but the previous model is not actually accuracte because the model has 2 neurons in the output layer but for the binary classification it should be 1 also it uses softmax activation for the output layer but the recommended for binary classification is sigmoid also it uses the categorical_crossentropy as the loss function but the recommended is binary_crossentropy.

However if you want me to improve the evaluation scores more i can do that by hyperparameter tuning which will take couple of more days need to run some more experiments

It's better to increase the accuracy a bit. You can take your time and come up with better solution.

from dl-simplified.

Hey @abhisheks008 I'm done with the project.
I've forked your repository earlier so for making pull request should i just replace the files under this project folder and make pull request using the entire forked repository ?? or should i just create a seperate folder and make a pull request for that folder only ?? what should i do??

from dl-simplified.

Make a PR for your codes only.

from dl-simplified.

This issue is not going to work.

from dl-simplified.

Hello @kumar8074! Your issue #473 has been closed. Thank you for your contribution!

from dl-simplified.