–Use the student data of test results, create a fictitous variable of pass or fail.

Examples:

Check under kernels tab

https://www.kaggle.com/spscientist/students-performance-in-exams/kernels

https://www.kaggle.com/anaking/classification-mode…

Using the link above, follow the same steps:

Reading the dataset

Summarizing

Visualizing the dataset , please use visualization 1 ,2,3 or 4 as an example.

You can just do 1 visualization and explain why you want to choose only that visualization based on factors such as ethinicity, parental education, test prep course etc.

Then summarize about the visualization you did

Plot graphs for each visualization

You may choose bar/box/histogram or scatter which is easily understood by the user

Next step is build a model using the visualization

You can use either decision tree/random forest, linear regression or k means algorithm which ever algorithm will give the best accuracy for the model

Explain why you would choose that particular algorithm and not others

Explain confusion matrix for each of those

Final aim is that this dataset should be easily understood by anyone who sees the plots and good for business

Make sure you go through the link below and refer to kernels section for examples and build visualization and model on your own

Please perform each and every step including reading the dataset

https://www.kaggle.com/spscientist/students-performance-in-exams/kernels