Importance
of Data Analytics in Business
Data Analytics helps businesses and industries to make sense of large amounts of information for growth and development. Data Analytics is used to:
- Improve decision making
- Predict consumer trends and actions
- Increase business productivity
- Improve customer service
In Manufacturing, Data Analytics is used to identify patterns, measure impact, predict outcomes, analyze equipment failures, determine production bottlenecks, and supply chain deficiencies.
In Banking, Data Analytics is used to analyze customer transactions to create more personalized products and services.
Types
of Data Analytics
There are four types of Data
Analytics:
- Descriptive Analytics examines what happened within a
business based on historical data. An e.g., is in the banking industry to
assess credit risks by using the customers’ credit history to determine the
eligibility for another loan. It can also be used in the manufacturing
industry, where key performance indicators are monitored in dashboards to track
production quantities to analyze and optimize maintenance level.
- Diagnostic Analytics seeks to delve deeper in order to
understand why something happened. This analytics looks at past performance to
determine what happened and why. E.g., social media marketers can investigate
campaigns and determine why they are successful or unsuccessful. Similarly,
freight companies can investigate the cause of slow shipments in a certain area
or region.
- Predictive Analytics analyses data based on past
patterns and trends, data analysts can devise predictive models which estimate
the likelihood of a future event or outcome. E.g., Hotels can predict how much
revenue a new service would generate from a given region. In Marketing,
predictive analytics is used for customer segmentation to determine which leads
have the best chance of converting.
- Prescriptive Analytics looks at what and why it happened
and also what might happen in order to determine what is next. It shows you how
you can take advantage of the future outcomes that have been predicted and what
steps you can take to avoid a future problem. E.g., Healthcare providers can
analyze clinically obese patient records, add filters for factors like
diabetes, to determine where to focus treatment. In the financial sector, a
machine learning algorithm can be trained to analyze stock market data and
automate human decision by making decisions based on large amounts of internal
and external data.
Data Analytics Process
Data analysis is a business process of collection, organization, modelling and interpretation of data in order to analyze the data for decision making. There are seven sequential steps:
- Data Requirements Specification: This determines what to measure and how to measure it. E.g. Which factors are negatively impacting the customer experience?” or “How can we boost customer retention while minimizing costs?”
- Data Collection: The goal is to find data that is relevant to solving the problem or supports an analytical solution of the requirements specification. Hence, data is collected from various sources ranging from organizational databases to the information in web pages.
- Data Processing: The raw data must be converted into a usable format. E.g., the data may have to be placed into rows and columns in a table within a spreadsheet or statistical application.
- Data Cleaning: The processed data may be incomplete or contain errors. Data cleaning corrects these errors. E.g., while cleaning the financial data, certain totals might be compared against reliable published numbers
- Data Analysis: The processed data is now ready for analysis and various data analysis techniques are applied to understand, interpret, and derive conclusions based on the requirements.
- Data Visualization: The data is examined and displayed in graphical format, to obtain additional insight regarding the messages within the data. E.g., Statistical data models such as correlation and regression analysis can be used to identify the relations among the data variables.
- Communication: The results of the data analysis are reported in a required format to be used to support decisions and further actions.
Data Types analyzed in Data
Analytics
- Relational Data: is generic data residing in
relational databases, which uses tables that can be linked based on the
commonality between each.
- Transactional Data: is the elements that support the
on-going operations of an organization that are included in the application systems
that automate key business processes. This includes a Flat File record for each
transaction.
- Time Related/Sequence Data: is a collection of observations
obtained through repeated measurements over time. E.g., Stock exchange records
and temperature sensor records.
- Stream Data: is data constantly being streamed.
It originates from some measurable activity triggered by a specific event that
happens as a direct result of an action or set of actions, like a financial
transaction, equipment failure, a social post or a website click.
- Hyper Text Data: is multimedia data, i.e., data
sources in the form of text, video, image, maps, or sound.
Data
Types Examples
Relational Data
In Banking, relational data is
gathered to optimize operations, e.g., a Human Resource Management (HRM) System
stores employee personal records such as names, dates of birth and addresses,
and also in Customer Relationship Management (CRM) Systems that stores customer
information e.g. credit card information.
In manufacturing, relational data is
used in the form of detailed information about electrical, mechanical,
chemical, or other parameters of system components and their applications, this
enables production to be automated and ensures data integrity (Scheyder, 1990).
Transactional Data
The Banking sector analyzes customer
transactional data such as ATM withdrawals and credit card spending for a
comprehensive understanding of a person’s financial position as well as
consumer behaviour. The outcome can be used to determine loans and incentive
rewards to customers.
In Manufacturing, transactional data
is created and updated within the operational systems. E.g., Wisynco bottles a
batch of drinks in a production database that is updated with the batch code
and expiry information. This information is also printed on the bottles and
data is collected at every stage of production including data from machines and
devices that makes up the transactional data.
Time Related/Sequence Data
In Banking, Time Related/Sequence
Data, such as share price movements are tracked over a period of time on the
various stock exchanges and analyzed to optimize investment returns. Also,
changes in web applications and network performance such as latency and
bandwidth utilization over time is tracked to help find root causes of
problems.
In Manufacturing, Time
Related/Sequence Data from sensors is used to detect and alert where anomalies
arise in processes that deviate from expected range, E.g., rum temperature data
from a distillery machine is tracked to ensure the product is made
successfully.
Stream Data
In Banking, Stream Data can come
from web and mobile device interactions and is used to detect fraud in real
time so that bankers can respond quickly to financial irregularities. E.g., a
hacker can be detected and identified by their web interactions and devices
used.
In Manufacturing, Stream Data can
originate from the Internet of Things (IoT) and machine sensors which can be
used to optimize production through preventative maintenance. Manufacturers
analyze stream data to prevent catastrophe when they monitor and detect issues
using vibration data streamed from machines over Bluetooth technology.
Vibration levels of machines are analyzed to determine how healthy the
components are.
Hyper-Text Data
In Banking, Hyper-Text Data in the
form of unstructured texts such as posts from various social media platforms is
used to find meaningful information. The hyper-text data is analyzed to detect
exact patterns and find useful information such as customer sentiment so that
new financial products are created and marketed.
In Manufacturing, Hyper-Text Data in
the form of video from CCTV is processed with indexing, automatic segmentation,
content-based retrieval and detecting triggers. This is then used in various
applications like security and surveillance, and education programs that the
manufacturer has in place.
Types of Databases used in Data Analytics
Relational (Structured) Databases
A relational database is a type of
database that stores and provides access to data points that are related to one
another. Relational databases are based on the relational model, an intuitive,
straightforward way of representing data in tables. In a relational database,
each row in the table is a record with a unique ID called the key. The columns
of the table hold attributes of the data, and each record usually has a value
for each attribute, making it easy to establish the relationships among data
points.
Relational databases are used to
track inventories, process ecommerce transactions, manage huge amounts of
mission-critical customer information, and much more. A relational database can
be considered for any information need in which data points relate to each
other and must be managed in a secure, rules-based, consistent way. Examples of
relational database include Oracle and MySQL.
Open
(Unstructured) Databases
Unstructured
database is data that doesn’t have a predefined schema or data model. It’s the
opposite of structured data, which is typically used in traditional relational
database systems (RDBMS), and formatted in rows & columns. Unstructured
data can be managed with more modern technologies such as NoSQL databases, data
lakes and data warehouses. Examples of Open Databases include Firebase database
and the Cloud.
Big
Data
Big
data is a term that describes the large volume of data – both structured and
unstructured – that inundates a business on a day-to-day basis. Big data can be
analyzed for insights that lead to better decisions and strategic business moves.
Big
Data helps organizations to create new growth opportunities and entirely new
categories of companies that can combine and analyze industry data. It is also
important in cost saving, time saving and marketing insights.
References
Scheyder E.C. (1990) Relational
Database Applications in Manufacturing System Design. In: Tjoa A.M., Wagner R.
(eds) Database and Expert Systems Applications. Springer, Vienna, from https://doi.org/10.1007/978-3-7091-7553-8_15
The 4 Types of Data Analytics.
(n.d.). Retrieved January 11, 2021, from https://www.kdnuggets.com/2017/07/4-types-data-analytics.html
Four Types of Big Data Analytics and
Examples of Their Use. (n.d.). Retrieved January 11, 2021, from https://imaginenext.ingrammicro.com/data-center/four-types-of-big-data-analytics-and-examples-of-their-use
Stevens, E. (2020, May 05). What Are
the Different Types of Data Analysis? Retrieved January 12, 2021, from https://careerfoundry.com/en/blog/data-analytics/different-types-of-data-analysis/
Data Types: Structured vs.
Unstructured Data. (2019, March 22). Retrieved January 13, 2021, from https://www.bigdataframework.org/data-types-structured-vs-unstructured-data
