Student Performance Analysis Prediction Using Data Analytics

 

Objective

To analyse the students performance based on their academic data using data mining techniques.

Project Overview

In this technological world, data storage and analysis are a big challenge. The ultimate goal of this project is aimed at better analysis with improved accuracy of data. Its requirement is so simple, that needs only the data sources, which is then processed to compute the results in the form of the report through which we can easily analyze the performance of the student in an efficient way.

It also focuses on analyzing data which helps in categorizing and thereby motivating the students in their academics as well as flavoring the staffs to improvise the students to the next level.Finally, the students are grouped as a good performer, average performer, a bad performer based on their result analyzed from their academic data.

Proposed System

Career building is the most cherished part of every college student. For a graduate, it is necessary to have immense knowledge in their domain to get placed in a reputed company. This system applies data mining techniques to the academic dataset. The Academic data includes the Internal marks and the Assignment marks. The final semester marks are predicted from the internal marks each student.

The proposed system architecture is shown in the figure.

Figure: Proposed System Architecture

Module 1:Data Selection

The required data is collected from the academic institutions. The data should consist of student details with internal marks and assignment marks.

Module 2: Data Preparation

Data preparation is an important step in the data mining process. Data pre-processing, includes cleaning, normalization, transformation, feature extraction, and selection, etc.

Module 3: Implementation of Data Mining Techniques

The required data mining algorithm is implemented using Java in Netbeans. These algorithms are applied to the data set to analyze the student academic performance and the accuracy are calculated.

Module 4: Predicting End Semester Grades

Prediction is a data mining function that discovers the future characteristics of the data. The relationships between co-occurring items are expressed as association rules. Predictive techniques rules are used to predict the final grades of the students using cumulative test mark and assignment marks.

Module 5: Grouping Students Using Simple Cluster

The students are grouped based on their end semester grades. The good performing students are grouped in one group, the average performing students are grouped as a group and finally, poor performing students are grouped in a group.

Module 6: Data Visualization

The association between theextracted results is found, to give the accurate analysis of results. These analyzed results are then displayed in the pictorial format of bar charts for the easy analysis and better understanding of the user.

Software Requirements

• Weka 3.8
• Netbeans
• Visual Studio
• SQL Server 2008

Hardware Requirements

• Hard Disk – 1 TB or Above
• RAM required – 4 GB or Above
• Processor – Core i3 or Above