1

Week 5 Assignment

Week 5 Assignment

Navya Gurijala

University of the Cumberland's

Business Intelligence

ITS-531-A01

Dr. Abiodun Adeleke (Abbey)

06/05/2024
2

Week 5 Assignment

Chapter 8

Discussion Question

Question 1
Prescriptive analytics is highly connected with descriptive and predictive analytics,

creating a three-step strategy for solving business issues. Descriptive-analytics deals with

condensing historic data to explain what has occurred while; predictive-analytics employs

statistical models and machine learning to predict future occurrence of an event based on data

analysis of past events (Kohler & Strehler, 2019). On the other hand prescriptive analytics

takes it a notch higher to give information and suggestions of how things should be done in

order to arrive at certain results. This degree of analysis is not only used to forecast new

situations, but also to prescribe the most effective plans of action, which is useful for in

decision-making.

These analytics’ types are intertwined and compliment one another. Descriptive

analytics offer the basic information that is used in predictive models, but the latter help

advise on prescriptive strategies (Kohler & Strehler, 2019). Thus, these analytics forms when

integrated can help organizations not only extrapolate the insights about the past and

forecasts for the future but make the future happen in the desired way. This integration

enriches the activities of corporate strategic management and facilitates business operations;

hence, prescriptive analytics becomes a valuable part of the analytics spectrum.

Question 2
Static models and dynamic models vary along one main dimension, which is time and

change. Static models describe a system at a point instanmce in time with no time bound

characteristics incorporated into the model. They are less complex models and are applied in

case the conditions are known and fairly unchanging (Sharda & Delen, 2019). This include
3

Week 5 Assignment

the linear models such as regression models and the simplest trees called the decision trees.

On the other hand, dynamic models are used in consideration of time variations in a system’s

state. These models are slightly more elaborate and are used where the conditions are

constantly varying for instance in stock exchange prediction and car traffic characteristics.

This transition from a static model to a dynamic model takes place as and when a

situation demands more accurate and dynamic representations of actualization. To start with,

a static model may be adequate in providing insights on the fundamental trends and results

(Sharda & Delen, 2019). But in situations where more data is produced and more components

form a complex structure, transitional features and interconnections start to emerge as

mandatory. It further enables improving prognostications and making more effective

decisions giving a depiction of the system’s performance span. Therefore, dynamic models

can be used as a source of more comprehensive knowledge about the systems which are

inherently variable.

Question 3
The expectation maximization strategy of engendering decisions in uncertain business

environments affirms the best results will happen. This approach is defined by the what-if

approach where one narrows down to the best-case scenario hence making acceptable

decisions that maximise on the possible gains while probably minimising the risk at the back

of their mind (Sharda & Delen, 2019). This strategy is actually particularly useful in those

cases in which market risk is relatively high and the potential profit is fairly large. Therefore

by taking the best case including the assumption that a certain course of action will be

favorable, one can be in a position to take more aggressive steps which hold the potential for

greater benefits.
4

Week 5 Assignment

On the other hand, the pessimistic approach is the opposite of optimists as it assumes

that the worst can happen and prudence should be prioritized. Implementing this strategy,

decision-makers set emphasis on avoiding the worst that could happen, rather than on the best

results. This approach is helpful in situations whereby, the cost of risk is very costly and the

stakeholders are prone to avoid the risks as much as possible even if this would cost them

highly valued gains. In particular, the historical analysis tends to consider a worst-case

scenario, which provides additional protection against the occurrence of possibility outcomes.

Question 4
Specifying situations under risk tends to be used when solving problems under risk

since it offers a more coherent environment for decision-making. SSE under conditions of

risk defines the best estimate of distinct results where there is a specific level of risk, which

helps in decision making under risk (Kohler & Strehler, 2019). This kind of assumption

enables one to measure the degree of variation and assess the effects of various choices. It

can be considered that uncertainty can be quantitatively calculated and controlled as the

identified risk, thus allowing using the quantitative methods to manage risks and obtain more

accurate prognosis.

Also, when addressing the issue of risk as related to the problem of uncertainty, it

becomes easier to come up with robust solutions that may withstand the harsh scenarios. It

makes it possible to predict various outcomes and the probabilities of their occurrence

through the creation of models and simulations (Kohler & Strehler, 2019). This strategy is

particularly useful in a scenario where the systems are highly variable as in the case of traffic

signalization where the decision process must consider the possibility of several events. Thus,

framing uncertainty as a risk problem guarantees that the solutions, which are intended to be

implemented, will be efficient at the same time as they are resistant to adverse circumstances.
5

Week 5 Assignment

Exercise

Question 4
The United States of America Department of Homeland Security (DHS SC) today

employ different kinds of models and simulations in order to build on various strategies that

can bolster the government’s fight against terrorism. These models assist in risk assessment

and warning through examination of large amounts of data to detect issues and risks. For

example, the strategic framework that has been developed by the Department of Homeland

Security to counter terrorism, involves data models in detection and prevention of both

internal and external terrorisms. These models assist the DHS in linking intelligence data,

where the organization is then in a position to develop new or elaborate unsteadyist concepts

that may respond to new types of terrorism risks and enhance the safety of the country (DHS,

2022).

Other government agencies utilize models in like manner to increase their efficiency

of their goals. For instance, the application of simulations in the areas of military helps to

prepare the soldiers and also in strategies to counter terrorism. These simulators play a

significant role in foreseeing and analyzing the pattern of terrorisms acts with the aid of

information collected from social, economical as well as political aspects. This type of

approach would make sure that the attempts to fight terrorism get a lot of support from all the

branches. Moreover, these models help agencies enhance their capabilities and organize

resources needed for their functional excellence (AFCEA International, 2021). This was

evident from the measures outlined above, depicting the AS tarde modeling and simulation as

critical in the current fight against terrorism across the world.

Week 5 Assignment

Chapter 9

Discussion Question

Question 1
Big data can be characterized as a large amount of information that is gathered

continuously and is of high variety and volume. These datasets are characterized by the three

Vs: , volume, velocity and variety, these describe the amount, the frequency, and the

formatting of data coming from different sources (Awan et al. , 2022). Big Data is important

because it allows an organization to understand, decide and anticipate future behaviors

through analyzing large volumes of data that were previously unmanageable. It is evident that

Big Data management can open up the prospect of considerable competitive advantages,

therefore, rising efficiency, innovativeness, and levels of receptions’ satisfaction.

Big Data is gathered from different places, including social media interfaces, devices,

customer transactions, and mobile gadgets. With the advent of the digital age, the volume of

data produced has been accelerated, where all people’s interactions, measurements, and

purchases accumulate vast amounts of data (Awan et al. , 2022). This data is frequently

unrelational and can have an essay form or can be photos and videos. Due to the enormous

and disparate aspects of Big Data, qualitative tools and techniques are necessary in order to

extract value information hence could prove to be a strategic resource for organization that

seek to function in competitive intelligent environment.

Question 2
The future of Big Data is expected to be in similar constant development, as it will

remain crucial for a variety of industries as the volume of data increases more and more. Big

Data will continue to evolve with Artificial Intelligence (AI) and Machine Learning (ML)
7

Week 5 Assignment

that will improve it more in an aspect of offering the right conclusion and insights more

accurately (Sharda & Delen, 2019). These technologies will help in processing the data at a

very high speed and will also add features to make Big Data even more effective tool for

decision making and innovation.

However, Big Data could be another example of a buzzword similar to, that of

quantum computing and the edge computing technologies. Quantum computing is understood

to be the process of solving certain problems at the speed expected from the future quantum

computing systems and the potential of revolutionizing data processing is highly debated

(Sharda & Delen, 2019). Edge computing is another approach which aims at receiving,

processing, and analyzing data closer to its origin to minimize response time and overhead.

By interconnecting these concepts, they could advance Big Data analytics to more intelligent

and adaptable data-enabled applications.

Question 3
Big Data analytics can be defined as the systematic and comprehensive analysis of

huge and diverse pieces of information in order to identify underlying patterns or

significance, trends, and opportunities in the market among others. While regular analytics is

majorly concerned with structured data derived from conventional databases, Big Data

analytics entails heterogeneously-large-scaled data, unstructured and semi-structured data

from various sources, for instance, social media, sensors and transactional systems as defined

by Awan et al. , (2022). As the name suggests, big data solutions can involve the use of

complex analytical tools such as machine learning, artificial intelligence and high end

algorithms to analyze big data at large amounts of extent in a very short time period.

The two concepts, Big Data analytics and regular analytics are often used to show

how a business operates and analyze the data it processes, but there is a huge difference
8

Week 5 Assignment

between the two forms of analysis in terms of the quantities of data that they handle. More

traditionally, advertizing relies on big data, but only has the capability to perform regular

analytics on a subset of data and often only in a smaller pool. On the other hand, Big Data

analytics have capacities of processing petabytes of data in real-time, and gives a broader and

richer insight about an organization (Awan et al. , 2022). This capability can lead to improved

decisions for the firm, forecasts and new ways of defining and recognizing patterns that are

difficult, if not impossible, to detect using traditional analytical techniques. Hence, capability

to make information a source of competitive advantage is boosted by Big Data analytics.

Question 4
The elements that are crucial for Big Data analytics are as follows: There must be a

clear strategy in place for the project, there must be competent and efficient infrastructure for

the project, and finally there must be staff with expertise in the project. A clear approach

helps to design and communicate the desired Big Data vision and establish what needs to be

done to make Big Data work in support of organizational objectives (Sharda & Delen, 2019).

It is the process of defining the scope of the business problem, definition of data source, and

definition of measure. Also, the availability of adequate, flexible, and cost-effective and,

storage systems and servers for handling the large volumes and diverse types of Big Data,

plus fast processing tools and efficient data integration tools and processes are requisites for

dealing with Big Data.

However, the effectiveness and applicability of Big Data analytics to face critical

challenges strictly depend on the employed experts. Fortunately, because of the increasing

complexity of business problems, skilled data scientists, analysts, and IT professions are

needed to manage datasets efficiently (Sharda & Delen, 2019). The environmental data must

be processed using the most sophisticated analytical approaches, and the application of
9

Week 5 Assignment

advanced machine learning techniques is seen as an imperative. Additionally, encouraging a

data culture in the organization promotes data sharing, cooperation, and creativity within the

organization establishing, utilizing data, and enhancing performance in the business

consistently.

Question 5
Challenges associated with BI & Big Data include; Data quality and integration that is

associated with the implementation of Big Data analytics. The quality of the data that is to be

employed is paramount since using poor information will lead to the development of

compromised conclusions and strategies. Overcoming the issue of having data from different

sources with different structures and formats is quite a challenge and can be very time-

consuming (Awan et al. , 2022). This process is done with sound data management best

practices and the right technical and state of art tools to transform data for analysis. As

highlighted above, the following are the common issues that are likely to affect big data

analytics implementations:

Another important challenge is data protection There is the constant and considerable

threat of exposure of data. A consequence of the Big Data processing large volumes of

citizens’ personal data and other Information assets is the need to safeguard against threats

and meet legal obligations (Awan et al. , 2022). Corporations need to put up a sophisticated

means of security and have this area closely scrutinized to avoid leakage of information.

Further, the technologies are fast- changing and this means that organization need to transfer

capital in funding new tools, as well as training human resources in fighting new threats and

improving in analytical technologies. Overcoming these challenges is pivotal for this strategy

regardless the type of development: its implementation and long-term positive consequences.
10

Week 5 Assignment

Exercise

Question 3
Big Data analytics is ideal for sports as it brings changes in performance, strategies,

and fans’ interaction. Another important application of BiS is performance analysis, where

athletes’ biometric data and statistics, collected during the games, are stored and analyzed to

determinate better ways of training and playing (Teradata University Network, n. d. ). This

information is used by coaches and analysts to devise training regimes, to assess players’

possibilities and impossibilities, as well as to influence the strategies employed during

matches. It means that timely interventions can be made and optimum performance can be

achieved in the future games, therefore it benefits hockey teams.

One more important area of the Big Data usage in sports is the improvement of fans’

engagement and experience. Using the feedback from the social media, ticket sales and in-

stadium devices, the sports organizations manage to capture the fans’ behavior and their

preferences (Teradata University Network, n. d. ). The information is useful in developing

targeted marketing communication tactics, bettering commodities and services provided in

the stadiums, and, generally, increasing fans’ levels of satisfaction. For instance,

understanding the movement patterns of the fans in a stadium can help in the placement of

the concession stands and help to minimize the queues drastically enhance the game-day

experience. Moreover, attendance can also be predicted seeking to support the purpose of

proper utilization of resources in conducting a particular event. These applications

demonstrate how Big Data is already critical to the contemporary sports industry and fan

engagement.
11

Week 5 Assignment

Reference
AFCEA International. (2021). Modeling and Simulation Adds Insight on Terrorism.

Retrieved from https://www.afcea.org/content/modeling-and-simulation-adds-insight-

terrorism

Awan, U., Bhatti, S. H., Shamim, S., Khan, Z., Akhtar, P., & Balta, M. E. (2022). The Role

of Big Data Analytics in Manufacturing Agility and Performance: Moderation–

Mediation Analysis of Organizational Creativity and of the Involvement of Customers

as Data Analysts. British Journal of Management, 33(3), 1200–1220.

https://doi.org/10.1111/1467-8551.12549

Kohler, E., & Strehler, M. (2019). Traffic Signal Optimization: Combining Static and

Dynamic Models. Transportation Science, 53(1), 21–41.

https://doi.org/10.1287/trsc.2017.0760

Sharda, R., & Delen, D. (2019). Analytics, Data Science, & Artificial Intelligence (11th ed.).

Pearson Education (US). https://reader2.yuzu.com/books/9780135172940

Teradata University Network. (n.d.). Sports Analytics. Retrieved

from https://www.teradatauniversitynetwork.com

U.S. Department of Homeland Security. (2022). DHS Strategic Framework for Countering

Terrorism and Targeted Violence. Retrieved

from https://www.dhs.gov/publication/dhs-strategic-framework-countering-terrorism-

and-targeted-violence