Page 35 - FULL REPORT 30012024

2.3.2 Process in Big Data Analytics

The process of big data analytics involves several stages, which are described
as below.

i. Data Acquisition

Data from several sources, including structured, unstructured, and

semi-structured data forms, are gathered at this stage (H. Li, 2021). It

encompasses the process of gathering data from diverse sources such
as social media, websites, sensors, and databases.

ii. Data Storage

After data is collected, the data need to be stored in a way that can

easily access for analysis (H. Li, 2021). Traditional storage solutions

may not be able to handle the scale and complexity of the data due to
the huge amounts of data involved with big data. As a result, large

data settings frequently adopt distributed storage systems. Large
datasets may be stored and managed over a cluster of linked devices

using distributed storage systems, such as Hadoop Distributed File
System (HDFS) and cloud-based storage options.

iii. Data Management

In this phase, the data must be managed and organised to be accurate,
comprehensive, and current. To do this, data cleaning procedures may

be used to eliminate mistakes and discrepancies in the data (Rawat,
2021). This stage focuses on ensuring the accuracy, completeness,

and the data is up-to-date.

Data cleaning techniques play a significant role in achieving this

objective. Data cleaning involves identifying and rectifying errors,
inconsistencies, in the dataset. This process includes removing

duplicate records, handling missing values, correcting inaccurate

data, and standardizing formats and representations. By applying data
18