A synopsis on
BIG DATA AND ANALYTICS
AJAY KUMAR GARG ENGINEERING COLLEGE
Delhi - Meerut Expy, Ghaziabad, UP- 201009
Submitted by
APRIL 2023
BIG DATA AND ANALYTICS
INTRODUCTION
Big data analytics refers to the process of exponential growth of digital data,
collecting, processing, and analyzing businesses are generating and collecting
massive volumes of structured and more data than ever before, and big data
unstructured data to gain insights and make analytics provides a way to derive value
informed business decisions. With the from this data.
other visual aids to communicate the
The process of big data analytics typically insights derived from the analysis.
involves several stages, including data
collection, data preprocessing, data analysis, Big data analytics has a wide range of
and data visualization. In the data collection applications across various industries, such
stage, data is collected from various sources, as healthcare, finance, retail, and
such as social media, sensors, and weblogs. manufacturing. For example, in healthcare,
The data preprocessing stage involves big data analytics can be used to analyze
cleaning and transforming the data to patient data and identify potential health
prepare it for analysis. The data analysis risks, while in finance, it can be used to
stage uses various techniques, such as detect fraudulent transactions and improve
statistical analysis, data mining, and risk management.
machine learning, to identify patterns and
insights in the data. Finally, the data In summary, big data analytics is a powerful
visualization stage uses charts, graphs, and tool that enables businesses to leverage the
massive amounts of data they collect to gain improve business operations, and it will
insights and make informed decisions. It has continue to be a critical area of focus as data
the potential to transform industries and volumes continue to grow.
STEPS OF DATA ANALYSIS
OBJECTIVES
The objectives of big data can vary waste and inefficiencies, and automating
depending on the organization and industry, manual tasks.
but some common objectives of big data
include: 4.Drive innovation: Big data can uncover
new business opportunities and facilitate
1. Improve decision-making: Big data can innovation by identifying emerging trends,
provide insights and analytics that enable predicting market demand, and enabling
better decision-making across various experimentation and prototyping.
functions, such as finance, marketing,
operations, and human resources. 5.Mitigate risk: Big data can help
organizations identify and mitigate risk by
2.Enhance customer experience: By analyzing internal and external data sources,
analyzing customer data, organizations can monitoring threats in real-time, and
help the organization gain a better developing predictive models.
understanding of customer’s needs and
preferences, and can tailor their products 6.Improve product development: By
and services accordingly to improve analyzing customer feedback, usage data,
customer satisfaction. and market trends, organizations can
improve their product development
3.Increase operational efficiency: Big data processes, prioritize features and
can help optimize business processes by functionality, and develop more innovative
identifying areas for improvement, reducing and competitive products.
FLOW CHART DEPICTING THE OBJECTIVES OF BIG
DATA
SCOPE OF WORK ON BIG DATA ANALYTICS
Here's a written model for how a medicine 1.Identify business objectives: The first
company could implement big data analytics step is to define the company's business
to improve their operations: objectives and the specific areas where big
data analytics could provide the most value.
For example, the company may want to
improve their R&D process, optimize their 4.Build analytical models: With the
supply chain, or enhance their marketing infrastructure in place, the company can
efforts. begin building analytical models that
address their specific business objectives.
2.Define data sources: Once the objectives For example, they may use machine learning
are clear, the company needs to identify the algorithms to predict drug efficacy or patient
data sources that will be used to support outcomes, or they may use natural language
their analytics initiatives. This may include processing to analyze social media
internal data sources, such as electronic sentiment around their products.
medical records, clinical trial data, and sales 5.Test and refine models: Once the models
data, as well as external data sources, such are developed, they need to be tested and
as social media data, market research refined to ensure their accuracy and
reports, and public health data. effectiveness. This may involve running
simulations, conducting A/B tests, or
3.Design analytics infrastructure: The comparing the results of different analytical
next step is to design the infrastructure for models.
storing, processing, and analyzing the data.
This will involve selecting the appropriate 6.Deploy and monitor models: Once the
hardware and software tools, such as models are validated, they can be deployed
Hadoop, Spark, and machine learning into production and monitored over time to
libraries, as well as developing the necessary ensure their ongoing effectiveness. This may
data pipelines and integration points. involve integrating the models into existing
workflows, developing dashboards and
visualizations to monitor performance, and By following these steps, a medicine
conducting regular reviews and updates to company can leverage big data analytics to
ensure the models remain relevant. improve their operations, increase
efficiency, and drive innovation.
REFERENCES
[1]. Cuelogic.com-big data testing- [3].Techtarget/Definition-big data
understanding the complex world of data [4].bdataanalytics-articles
testing [5].bleuwire-images
[2]. Chat.openai.com/
