Student Grade Prediction is a way of predicting a student grade based on his/her previous marks. To provide User_friendly environment a web page is also created through which any student can enter his/her previous three years marks in the web page by using web link provided then after entering they click on the submit button. After pressing the submit button then it will be directed to another tab which contains the GRADE of that student followed by a message about his/her capabilities.
This also makes the student know whether he/she is in a position to reach his/her expected marks or not. If this model shows that he/she needs to improve then that student can prepare more for that semester so that he/she can reach their expected score.
By using web Link one can access the page easily and can enter his/her details.
By using them the model will Predict the GRADE of the student based on his/her previous marks.
Model can even predict whether he/she will pass/fail in the next semester
A message will also be given based on his/her Grade Such as:
1. If the student grade is “A” then the message is “You Are Excellent”.
2. If the student grade is “B” then the message is “You Are Good”.
3. If the student grade is “C” then the message is “You Are OK”.
4. If the student grade is “D” then the message is “You Need To Improve”.
5 .If the student grade is “F” then the message is “You Need To WorkHard”.
By that message the student can prepare according to that.
Student Grade prediction is a model which is designed using “Machine Learning” technology. Machine Learning means predicting the present based on past scenarios and predicting the future based on past and present scenarios. The algorithm used for this model is “K-Nearest Neighbour” which is a Classification algorithm.The attributes used for designing this model are:
Steps involved in Machine Learning:-
A machine learning project involves the following steps:
- Defining a problem
- Preparing data
- Evaluating algorithms
- Improving results
- Presenting results
The best way to get started using python for machine learning to work through a project end-to-end and cover the key steps like loading data, summarizing data, evaluating algorithms and making some predictions.
This gives you a replicable method that can be used dataset after dataset, you can also add further data and improve the results.
Libraries and Packages:-
Libraries and packages to understand machine learning. You need to have basic knowledge of python programming. In addition, there is a number of libraries and packages generally used in performing various machine learning tasks as listed below:
- Numpy-is used for its N-Dimensional array objects.
- Pandas-is a data analysis library that includes data frames
- Matplotlib-is 2D plotting library for creating graphs and plots
- Scikit-Learn- the algorithms used for data analysis and data mining tasks.
- Admission Type
- Family support
- 1-1 mid percentage
- 1-1 semester percentage
- 1-2 mid percentage
- 1-2 semester percentage
- 2-2- mid percentage
- 2-2 semester percentage
- 3-1 mid percentage
- 3-1 semester percentage
- 3-2 mid percentage
- 3-2 semester percentage
- Technical skills
- Final Grade
- KNN can be used for both classification and Regression predictive problems.
However it is more widely used in classification problems in the industry.
- Easy to interpret the output.
- Calculation time.
- Predictive power.
- KNN is pretty intuitive and simple.
- KNN has no assumptions.
- Used for both classification and regression.
- Curse of dimensionality.
- KNN needs homogeneous features.
- KNN slow algorithm.
ATTRIBUTES AND THEIR DESCRIPTION:-
|Attribute Number||Attribute Name||Description||Domain|
|3||Locality||Place where student’s live.||U/R|
|4||Campus||Block which belongs to particular student.||AEC/ACET/ACOE|
|5||Reason||Why they selected that particular campus||Reputation/Course/Availabilities/others|
|6||Admission Type||Type of Admission||Convener/Management|
|7||Branches||The course they selected.||CSE/ECE/MECH|
|8||Family support||Family support for education purpose||Y/N|
|9||1-1 mid percentage||Student 1st mid Average||1-100|
|10||1-1 semester percenatge||Student 1st semester Average||1-100|
|11||1-2 mid percenatge||Student 2nd mid Average||1-100|
|12||1-2 semester percentage||Student 1st semester Average||1-100|
|13||2-1 mid percentage||Student 1st mid Average||1-100|
|14||2-1 semester percentage||Student 2nd semester Average||1-100|
|15||2-2 mid percentage||Student 2nd mid Average||1-100|
|16||2-2 semester percentage||Student 2nd semester Average||1-100|
|17||3-1 mid percentage||Student 1st mid Average||1-100|
|18||3-1 semester percentage||Student 3rd semester Average||1-100|
|19||3-2 mid percentage||Student 2nd mid Average||1-100|
|19||3-2 semester percentage||Student 3rd semester Average||1-100|
|20||Backlogs||Backlogs that a student have.||0-31|
|21||Tech skills||Technical skills that student have||Y/N|
|23||Events||Student participated in particular events.||Y/N|
|24||Final grade||Student Final Grade||A,B,C,D,F|
BUILDING A WEB PAGE:-
In order to make this project user-friendly we designed a webpage through which everyone can access the web page by using the web link
The User has to enter his/her details in that web page then that input will be inserted into the database
From that SQL database, the ML program will take the input and will be given to the model for prediction
Now as the model had been already trained it will predict the category of the particular student and show the final classified class label on the screen which will be displayed on a new tab.
Our main motive is to help students to know their capabilities and also their weaknesses so that they can make use of those capabilities and work even more on them to get great opportunities and also to make them know their weaknesses so that they can strive hard to overcome them and then achieve their expected scores. College can also use this to know how many students are going to pass and how many students are going to fail so that they can prepare students according to their score and category.
A.Nineesha Bhavani- email@example.com