Designing an ML Prediction Model for Loan Eligibility || Loan dataset Prediction || Thinkswithyou
ping me on whatsaap if you have any question +92 343 9293686
Description:
TASK 1:
1. What are regression and classification ML techniques? Explain in about 500 words how these techniques are helpful in different sectors?
2. Explain overfitting and underfitting? How to combat Overfitting and Underfitting problems?
3. Can you explain the difference between validation set and a test set?
4. Explain SVM algorithm with an example?
5. Explain the Decision Tree algorithm and how it works?
6. What is forward and backward propagation and explain its working?
TASK 2:
Design and develop the ML prediction model for a given scenario and produce the report A newly established bank “Bank ABC is eager to develop a Loan Eligibility Prediction Model based on the applicants’ information. Currently, Bank ABC issuing a paper-based system to check the eligibility of applicants and it is a lengthy process to approve or reject the loan. The bank receives many applications every day and they need more time and staff to check the eligibility whether the applicant is eligible to take the loan or not. Therefore, to save time and cost, the bank is intending to develop an automation system by developing a computer-based loan eligibility prediction model. Assume that the bank has hired you to design and develop a model based on your expertise in Machine Learning. And you will need to design and develop ML models to automate their process.
Data: The datasets are available to download from ML module in Moodle. You are given two set of data to develop ML prediction model LoanDatasets.csv – to train the model LoanDataset_test.csv – to test the model
Code: We are looking of to show your coding skills using python programming language and Jupyter Notebook.
Challenge: We would like you to work towards the above scenario to predict loan eligibility of the applicants for YB Bank.
Activity: You could focus on the following
1. Data collection
2. Data preparation (cleaning, feature selection, feature engineering, etc.,) - Ensure you carry out the data cleaning process for the machine learning model once you explore and visualise the dataset. Provide detailed evidence of the process in the report.
3. Split the dataset for training and testing in your machine learning model. Split the dataset into different portions and observe the model output and see how it impacts the performance of the model
4. Data visualization – Visualise the trend and pattern in data using bar chart, histogram, line chart, scatter plot, etc.,
5. ML modelling (building and testing a predictive model) - Use suitable machine learning technique to model the dataset. Explain the rationale behind choosing your machine learning technique. Evaluate and compare the performance of the model using a different machine learning algorithm to the same dataset.
6. Model performance and evaluation - Evaluate the performance and effectiveness of the model – (with training, testing and new datasets and compare model’s output and write findings with valid justification). Evaluate the trained model by predicting some input data.
7. Optimise the model by tuning the hyper parameters to get a better accuracy. (Use R-squared to find the accuracy of the model) You should support your code implementation with written documentation for Task 2(must cover all the above points
#Loaneligibilitypredictionpython
#Loaneligibilitypredictioncalculator
#Loaneligibilitypredictiondataset
#Loaneligibilitypredictioninmachinelearning
#loaneligibilitypredictionresearchpaper
#loaneligibilitydataset
#loanpredictiondatasetcsv
#loanpredictionkaggle
Watch video Designing an ML Prediction Model for Loan Eligibility || Loan dataset Prediction || Thinkswithyou online without registration, duration hours minute second in high quality. This video was added by user Thinkswithyou 06 December 2023, don't forget to share it with your friends and acquaintances, it has been viewed on our site 1 once and liked it people.