CCP Assignment Data Science 03062022 121250pm
CCP Assignment Data Science 03062022 121250pm
ASSIGNMENT No. 3
Complex Computing Problem
Maximum Marks: 10
Instructions
1. This assignment is a complex computing problem (CCP) which can be performed
individually or in a group of 2 students.
2. Assignment should be done only on A4-size paper and will also be uploaded on
LMS.
3. Deadline will not be extended for any reason.
4. Viva will be conducted at the time of assignment submission.
5. Copied assignments would have zero marks.
6. Individual efforts would be appreciated.
7. Name, class, section, department and roll number on the sheet must be mentioned
clearly.
Semester project is designed in a way to enable students to solve the complex computing
problem. Following characteristics of complex computing problem are targeted in this
semester project of data science.
CCP Statement:
Due to exponential data growth, organization and businesses want to make full use of
data they have produced so far. Data analytics is the process of examining this data in
order to find trends and draw conclusions about the information they contain. Several data
analytics/science techniques are used in this regard. These include
supervised/unsupervised learning techniques, feature selection, missing data imputation,
outlier detection, data smoothing, etc. The purpose of this assignment is to evaluate these
techniques on any data analytics/science problems mentioned below. The selection of
these techniques is based on the problem of your choice. The below mentioned list of
problem categories can be used for problem selection, while you are also free to choose
any data science problem other than the list given below. Apply all necessary data science
tools to preprocess and then analyze the dataset taken from any public repository (like
Kaggle and UCI).
Problems categories:
1. House Price Prediction
2. Building Energy Efficiency Classification
3. Customer Segmentation
4. Mobile Price Classification
5. Student Performance Analysis
6. Bank Subscription Classification
7. Store Sales Prediction
8. Bank Loan Default Prediction
9. Heart Disease Analysis
10. Sentiment Analysis
You are required to analyze the problem in following four phases, and prepare a detailed
report.
Problem Identification:
In the first phase, you will discuss and analyze the problem you intend to work on.
Counselling will be given to you for finalizing your idea and preparing a proposal. You
are deemed to explore the problems/issues around your selected proposal, which you can
solve using data analytics/science tools and algorithms. If you analyze the problem found
irrelevant to solve this level problem, the assignment will be considered cancelled.
Project Proposal:
In initial study phase, you must explore the literature or existing solutions for your
selected project idea. In this phase, you are also encouraged to have a detailed analysis of
the problem to solve it in a efficient way. Each student’s/group’s project should be
unique, and may have many possible solutions as well as may be explored and developed
in different ways. After discussion, you are asked to submit a proposal on one idea
approved by the instructor.
Simulation of Project:
Every project is checked by running and observing the output. You have option of using
any software development tool for the project. You are required to apply the in-depth
computing knowledge (2) to complete each project. During the initial study and
formulation of proposed solution, you are supposed to focus on the detailed requirements
(5), real-time constraints (5) and performed in-depth analysis (1). Projects were
evaluated on the following criteria:
Summary: