USE OF BIG DATA IN EDUCATION SECTOR
INTRODUCTION
In recent days most of the sectors are using data driven decision making technique which involves in collecting the data according to the objective of the work to be done, analyze the data, utilize the output in developing the strategies for the benefit of the work. Big data, Business Intelligence and Analytics technology are the most used technologies in the field of data science to get insights from previous data and make future predictions.
BIG DATA, BUSINESS INTELLIGENCE AND BUSINESS ANALYTICS
‘Big Data’ is a large set of data which is analyzed by the help of computer software to reveal pattern, trend and association relating to any situation. It helps in rapid development of new capabilities of the technology to generate new opportunities against the problem.
‘Big Data’ is defined with the help of three V s –
1. Volume of the data that are being gathered which has low density and which is unstructured in nature.
2. Velocity of the data is defined as how fast the data is received and acted on a particular action.
3. Variety of data is defined as the types of data available. Data are mainly of three types- Structured, Semi- structured and Unstructured data.
‘Business Intelligence’ and ‘Business Analytics’ both utilize the data to get the solution from raw information and allows the organization to deliver better insights for making better future decision.
‘Business Intelligence’ (BI) mainly focus on descriptive analytics method which provides a summary of historical data or present data to show what happened in the past or what is happening now. While ‘Business Analytics’ (BA) focus on predictive analytics which use data mining and machine learning tool to predict the future.
STATISTICAL METHOD
Statistics is the powerful tool in the field of data science. Using statistics, we can go deep and find fine insights of data. There are mainly 5 statistics concepts that are used in data science –
1. Graphical Plots — Box plot, Scatter plot, Histogram, Pie chart etc helps in analyzing or visualizing the data.
2. Probability Distribution — Uniform distribution, Normal distribution, Poison distribution, Binomial distribution etc are used in data analysis.
3. Dimensionality Reduction Technology — it helps in reducing the unimportant features from the analysis.
4. Over and Under sampling technique — This technique is used for classification of data set into majority and minority class.
5. Bayesian Statistics — It is based on frequency analysis, how frequently an event is about to occur in the form of probability.
BIG DATA TECHNOLOGIES
SAS, Microsoft, IBM, Oracle are the major vendor of data analytics tool in Big Data industry. The lists of big data technologies offered by the vendors are infinity. Few of them are –
1. Hadoop:- It is an open source framework of application of Big Data.
2. Spark:- It is a part of Hadoop ecosystem. It is an engine for processing big data within Hadoop with hundred times faster speed than the standard Hadoop engine (MapReduce)
3. R- language:- It a programming language with software environment designed for working with statistics.
4. Data Storage:- Big Data is always having a huge number of data sets. To store the data safely a massive amount of storage is required. Cloud storage is the most significant storage system with respect to safety as well as cost of storage. One of the most popular cloud storage vendors is ‘Amazon.’
5. Cloud Computing:- It provides computing service through the internet. This type of service is allowed to focus on the data analysis part rather than focusing on data collection method and data quality.
The other Big Data solution techniques are –
Data Lakes, NoSQL database, In Memory Database, Predictive Analytics, Big Data Security Solutions, Artificial Intelligence, Edge Computing etc.
BIG DATA ANALYTICAL METHOD
Different analytical methods can be applied for ‘Big Data Analysis’.
1. Basic Statistics:- There are mainly two types of statistical methods used in big data analysis — Descriptive Statistics, Inferential Statistics.
Descriptive statistics helps in measuring the central tendency of data such as mean, median, mode, variance, standard deviation, range and distribution of the data.
While Inferential statistics used for hypothesis testing which include parametric and non-parametric analysis.
2. Information Visualization:- It is a data visualization technique with the help of ‘human computer interaction.’ It helps in visualizing the performance by converting the complex data into computer generated graphics.
3. Classifiers:- It is a data mining technique. Classification of data can be done in two steps — First we need to choose the data classification technique such as decision tree, neural network etc. Second we need to select the data set with known class value.
4. Cluster Analysis — It is used for explanatory data analysis to find the degree of association between the target variable is maximum if they belong to the same group and vice versa.
5. Association Rule Mining:- It helps in discovering relationships among various attributes in data sets.
Other methods are-
- Association rule learning
- Classification tree analysis
- Genetic algorithms
- Machine learning
- Regression analysis
- Sentiment analysis
- Social network analysis etc
APPLICATION OF BIG DATA IN EDUCATION SECTOR
Big Data and Analytics can be used in various sections in higher education, like — admission process, financial planning, administrative functions, student performance, placement and recruitment etc.
1. Administrative function and Admission process:- The entire application process for admission is based on data collection of the applicant by generating the unique applicant identification number. The data can be used to analyze the student’s past performance. The online exam given by the student helps in analyzing the capability and give rank accordingly.
2. Student Success:- Most of the educational institute collect the data using ‘Enterprise Resource Planning’ (ERP) and ‘Learning Management System’ (LMS). The collected data can be used to analyze relationship among various variable associated to student performance to predict student success. ‘LMS’ helps in understanding the satisfaction level of a student with their teachers by finding the correlation between the teaching and success of student.
3. E-Books and Mobile Device:- E-books are becoming a trend for the students. The numbers of registration for e-books are increasing day by day. This actually provides an opportunity for additional data mining with the help of book usage, course content, how much time a student is spending on a particular page etc. So basically it helps in getting the data of reading pattern of a student and suggests the publisher for customization.
4. Finance and Budget:- Finance and Budget actually helps in ‘Market entry strategy’ for a business. It helps in generating different kinds of business model and help in accessing the feasible solution to enter into a new market. Educational institute can also use this technique to enter into new market or can develop future operations strategies.
BENEFITS OF BIG DATA IN EDUCATION
1. Can improve students’ performance and learning abilities making the lessons more customized according to the ability of the student.
2. Helps in identifying best educational institute for a student by comparing the requirement and the past performance of the student.
3. In terms of employment, student can find and make application for jobs which can match their abilities.
CONCLUSION
Big Data can lead to big benefits in educational sector. It can afford to shape a modern and dynamic education system which every individual student can have the maximum benefit from it. But there are always some problem related to ethical considerations, capturing data electronically and lack of experts in the area of big data and analytics. By overcoming all the challenges, Big Data is used in many educational institutes to understand different topics such as — administrative and admission process, student performance, placement and recruitment etc. Hence Big Data are actually involved to change the way of educational institutes. By this the educational system will enrich new learning methods by making the path more efficient and targeted.
