Enhancement of Bank Loan Approval Prediction

[abhisheks008]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Enhancement of Bank Loan Approval Prediction
:red_circle: Aim : The existing Bank Loan Approval Prediction project is developed using a single neural network model. The aim is to enhance the project by adding new models for this project which will make this project more compact and accurate based on the accuracy scores.
:red_circle: Dataset : Mentioned in the dataset folder of the project.
:red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name :
• GitHub Profile Link :
• Email ID :
• Participant ID (if applicable):
• Approach for this Project :
• What is your participant role? (Mention the Open Source program)

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[Vaidehi-Shende]

Full name : Vaidehi Shende GitHub Profile Link : https://github.com/Vaidehi-Shende Email ID : vaidehishende2003@gmail.com 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

[abhisheks008]

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

[Vaidehi-Shende]

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.

[abhisheks008]

Assigned to @Vaidehi-Shende under SWOC S4.

[kumar8074]

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

Full name : Lalan Kumar GitHub Profile Link : https://github.com/kumar8074 Email ID : lalan.k8977@gmail.com 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

[abhisheks008]

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

[kumar8074]

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

Yes absolutely @abhisheks008

[abhisheks008]

Cool. Issue assigned to you @kumar8074

[kumar8074]

Cool. Issue assigned to you @kumar8074

Thank you @abhisheks008

[kumar8074]

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?

[abhisheks008]

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.

[kumar8074]

OK got it

[kumar8074]

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

[abhisheks008]

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?

[kumar8074]

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

[abhisheks008]

Cool go ahead @kumar8074

[kumar8074]

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

[abhisheks008]

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.

[kumar8074]

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 👍

[kumar8074]

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??

[abhisheks008]

Make a PR for your codes only.

[abhisheks008]

This issue is not going to work.

[github-actions[bot]]

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