QAC020X354H - Data Science: Reflection, Comparison, Strengths Report

This data science report provides a comprehensive analysis of various concepts and techniques within the field. It begins with a reflection on a group project, focusing on planning, organization, teamwork, communication, negotiation, conflict resolution, and fair division of labor. The report then compares and contrasts traditional business intelligence with contemporary approaches, collaborative filtering with content-based filtering, semantic analysis with visual analysis, replication with sharding, and ACID with the CAP theorem. Finally, it examines the strengths and weaknesses of Hadoop distributed processing and event stream processing. The report concludes by emphasizing the importance of data science in modern organizations for managing and analyzing big data, advocating for the adoption of updated technologies for improved decision-making processes.

Data Science

Table of Contents

Introduction......................................................................................................................................1
Main Body.......................................................................................................................................1
Task 1: Reflection on project 1..............................................................................................1
Planning.............................................................................................................................1
Organisation.......................................................................................................................2
Teamwork..........................................................................................................................2
Communication..................................................................................................................2
Negotiation........................................................................................................................2
Conflict resolution.............................................................................................................2
Fair division of labour.......................................................................................................3
Own contribution to the group...........................................................................................3
Improvements for future and why.....................................................................................3
Task 2: Compare and contrast................................................................................................3
Traditional Business Intelligence Vs Contemporary Business Intelligence......................3
Collaborative Filtering Vs Content Based Filtering..........................................................4
Semantic Analysis Vs Visual Analysis..............................................................................4
Replication vs Sharding.....................................................................................................4
ACID vs CAP Theorem.....................................................................................................4
Task 3: Strengths and Weaknesses.........................................................................................5
Hadoop Distributed Processing.........................................................................................5
Event Stream Processing...................................................................................................5
Conclusion.......................................................................................................................................5
References........................................................................................................................................6

Introduction
Data science can be defined as the field of study which specifically uses the scientific
methods and algorithms along with the various types of processes and systems in order to extract
data and information so that the appropriate knowledge can be extracted from the structured or
unstructured data in order to apply such knowledge and insights in a wider range of different
application domains. It highly requires expertise and programming skills along with the
mathematics and statistics that show that the meaningful information is extracted from the raw
data. It is basically used in the business for better market research and analysis of the data for
better decision making process in an organization (Kelleher and Tierney, 2018). The following
discussion is based on the three tasks in which task1 specifies the reflection of group project 1
containing the planning and Organization along with the teamwork and communication which is
followed by the negotiation and conflict resolution and also the fair division of labor. Moreover,
contribution to the group and improvements for future and reason behind it is also discussed.
Task 2 includes the comparison and contrasting between the traditional business intelligence and
contemporary business intelligence, collaborative filtering and content based filtering, cement
analysis and visual analysis, replication and sharding and acid and Cap theorem. Task 3 includes
various strengths and weaknesses along with the applications of Hadoop distributed processing
and event stream processing with proper findings and conclusions.
Main Body
Task 1: Reflection on project 1
Planning
Group project was conducted on the topic of data science and hence proper planning was
needed and therefore the whole group followed the proper planning process while preparing for
the project in an effective and efficient manner so that the execution and implementation process
can be easy and comfortable for us. We have planned to first gain in-depth knowledge about data
science and then proceed with the work as per the knowledge each and every one has gained and
accordingly perform the task.
1

Organisation
Our whole group project was organized in a decent manner by following each and every
step of management from planning to controlling such as planning and then organization then
staffing where each and every member has assigned the task to conduct then directing and then
control in the whole project for better presentation.
Teamwork
We have demonstrated teamwork in the data science project by supporting each other in
their task so that they can be proficient in performing their job and can get the best of the
knowledge. There was proper guidance and direction each and everybody was given to each
other so that nobody can lack any confidence and can get motivated with the work.
Communication
There was a good communication flow among guys like not only we were talking on the
project work but also it was fun having the work with the team because it was or entertainment
going on such as formal and informal communication was highly supported in the teamwork so
that everybody can get comfortable with each other and Frank for better working environment
and culture in the project work.
Negotiation
Some members are having low negotiation skills and some members were having high
negotiation skills which means that decision making and influencing power is good of the
members who have good negotiation skills and therefore other members who have less
negotiation skills are having a problem in uttering the word also so therefore negotiation was at
an average level in our group.
Conflict resolution
Conflict resolution was also at an average level because leadership and mentorship was
not that much good and sufficient which is required by the group members so therefore there
were conflicts and resolution was also there but a problem is only that it was taking time in
getting resolved in an effective manner with perfection.
2

Fair division of labour
Fair version of labor was good in our group members because initially at the planning
stage we have divided it each and every task to all the group members in which they all are
proficient in and can you gain the knowledge easily so hence and the initial stage we have
divided each task to each member for better division off work in the data science project.
Own contribution to the group
I have contributed in the group while performing some tasks on data science as I have
performed the Internet browsing and referred many books and journals to gain knowledge about
data science so that my content and presentation can look justified and evidence to prove with
the relevant and reliable authors in the form of references. In my views, I have contributed well
in my whole project teamwork.
Improvements for future and why
Future improvements can be considered such as the negotiation and conflict resolution part
because these two elements were lacking in our group project therefore it is important for future
considerations that negotiation and conflict resolution can have better management for further
projects so that the team can work in harmony in a better decision making process.
Task 2: Compare and contrast
Traditional Business Intelligence Vs Contemporary Business
Intelligence
Differences between traditional business intelligence and contemporary business
intelligence are such that traditional business intelligence is its domain of information
Technology and the analyst community whereas contemporary business intelligence has the
environment which extends the utilisation of analytical techniques in an organization. Traditional
business intelligence focuses on the initial tactics which were formulated for basic operations
and Management in the company whereas contemporary business intelligence focuses on the
strategies which targets the goals and objectives of the organizations (Kotu and Deshpande,
2018).
3

Collaborative Filtering Vs Content Based Filtering
Difference between collaborative filtering and content based filtering and such that the
collaborative filtering demonstrates the user to user’s suggestions and recommendations which
mixes their features and items itself along with the preferences of other users whereas content
based filtering itself make suggestions and recommendations dependent on the preferences of the
users as per the features of the products (National Academies of Sciences, Engineering, and
Medicine, 2018).
Semantic Analysis Vs Visual Analysis
Difference between semantic analysis and visual analysis are such that semantic analysis
is the utilization of ontologies in order to analyze the various web resources containing content in
order to research combined text and relatedness of the ontological concepts whereas visual
analysis particularly focuses on the reasoning techniques and helps the users to gain the data
which directly supports decision making and other functional of the management it also
represents and interacts with various techniques in data science (Blum, Hopcroft and Kannan,
2020).
Replication vs Sharding
Difference between replication and sharding are such that replication supports the
horizontal scaling in order to read the data in a potential manner whereas starting permits the
horizontal scaling of information through partitioning of data across different types of servers
using the shared therefore it is important to select the good shared key for the operations (Cao,
2018).
ACID vs CAP Theorem
Difference between acid and Cap theorem are such that acid theorem is the consistency
which contains all the database rules in order to offer some of the acid properties over the
clusters where is cap theorem has a consistency to get involved in the substance which offers the
repeatable reads along with the comparison and full transactions insights. Cap consistency means
guarantee at any node (Hicks and Irizarry, 2018).
4

Task 3: Strengths and Weaknesses
Hadoop Distributed Processing
Hadoop distributed processing can be defined as the open source distributed processing
which has the structure and substructure that can manage big data processing and also stores the
large amount of data in applications to form the scalable clusters of different computer servers. It
is also known as the Apache Hadoop because this technology is introduced as a part of an open
source project under the project of Apache software foundation (Sanchez-Pinto, Luo and
Churpek, 2018).
Event Stream Processing
Event stream processing can be defined as the combination of various technologies which is
designed to support the construction of a sorted event-driven information systems and software
which includes the event visualization and event databases along with the event driven
middleware and event processing languages which is followed by the complex event processing.
All these are the elements of event stream processing which combined supports the information
systems for their better operations and management as per the needs and requirements of the
organizational function (Peyré and Cuturi, 2019).
Conclusion
It is concluded that data science is an important concept to learn and study so that its
applications can be applied in real world organizations for better adoption of the updated
Technology in the companies to manage the big data and analysis of it. Therefore, it is important
to analyze the various concepts of data science along with the reflection on it done in the
previous project. It is essential to examine the comparison and contrasting between different
elements of data science. It is necessary to determine the strengths and weaknesses along with
the different applications of various components of data science. hence this report covers all such
areas in order to better understand the conception of data science.
5

References
Books and Journals
Blum, A., Hopcroft, J. and Kannan, R., 2020. Foundations of data science. Cambridge
University Press.
Cao, L., 2018. Data science thinking. In Data Science Thinking (pp. 59-90). Springer, Cham.
Hicks, S.C. and Irizarry, R.A., 2018. A guide to teaching data science. The American
Statistician. 72(4). pp.382-391.
Kelleher, J.D. and Tierney, B., 2018. Data science. MIT Press.
Kotu, V. and Deshpande, B., 2018. Data science: concepts and practice. Morgan Kaufmann.
National Academies of Sciences, Engineering, and Medicine, 2018. Data science for
undergraduates: Opportunities and options. National Academies Press.
Peyré, G. and Cuturi, M., 2019. Computational optimal transport: With applications to data
science. Foundations and Trends® in Machine Learning. 11(5-6). pp.355-607.
Sanchez-Pinto, L.N., Luo, Y. and Churpek, M.M., 2018. Big data and data science in critical
care. Chest. 154(5). pp.1239-1248.
6