Machine Learning - Final Project Guideline

Version: 1.0

Revise date: 25-Oct-2024

SCOPE
This final project is designed to assess students' proficiency in Machine Learning. You will use
one or more machine learning algorithm to solve the assignment.

DELIVERY
The project will be considered successfully submitted when the following components are
delivered:
1. A comprehensive Jupyter Notebook or python file that includes scripts for loading,
cleaning, processing, analyzing, and modeling the data.
2. A presentation of up to 15 minutes, to be delivered by ALL group members, outlining the
Project problem statement, insights and outcomes.
3. A portfolio report (maximum 5 pages) following the ASM/IEEE template.
4. A self and peer evaluation form to assess each member’s contribution to the project.
Clearly state who perform which part (code, writing, etc..)

TIMELINE
1. Initiation: Students will begin by selecting a dataset and forming a project plan in the first
week.
2. Development: The following weeks will be dedicated to data analysis and model
development, with checkpoints for progress assessment.
3. Presentation Day: Scheduled towards the end of the project timeline. Absence on
presentation is not allowed, leading to 0 point of presentation part.
 4. Final Submission: All project components must be submitted at once by the specified
deadline and follow the Appendix Submission Guidelines.

DATASETS
https://drive.google.com/file/d/1FFg4bFW0LAFiWMFC2YUY1b8vBQulcsuk/view?usp=sharin
g

EVALUATION
The project will only be evaluated once all components have been submitted by the deadline.
Incomplete submissions will result in a grade of 'Incomplete,' affecting the course outcome.
Projects will be graded on a scale of 20 points, with each category having an equal weight of 5
points.
1. Analytical Rigor (max 5): Thoroughness in data processing, analysis, and model
accuracy.
2. Innovation and Complexity (max 5): Application of innovative analytical methods and
complex model features.
3. Presentation and Report (max 5): Effectiveness in conveying the project's scope, process,
results, and insights.
4. Peer Review (max 5): Evaluation of teamwork dynamics and individual contributions as
perceived by peers.
Note: A score of zero for any category indicates a failure to meet the requirements for that
particular aspect of the project.

Project Rubric
Category 5 Points 4 Points 3 Points 2 Points 1 Point 0 Points
Exceptionally Thorough in Adequate data Inconsistent Poor data
No significant
thorough in data processing and data processing processing and data
Analytial data processing and analysis; and analysis; analysis; processing,
analysis, or
Rigor processing and analysis; models are models have models lack
model
analysis; models are reasonably limited accuracy and accuracy.
models are accurate and accurate with accuracy and validation. Little to no
 highly validated. some validation. Significant data use of
accurate and Most data validation. Data Some key data processing steps PySpark for
data
well-validated. processing processing steps processing steps are missing or
processing.
All data steps are clear are sufficiently are missing or poorly
loading, and detailed but inadequately executed.
cleaning, comprehensive may lack some explained.
processing, . depth.
and analyzing
steps are
detailed and
comprehensive
.
Highly
innovative
Innovative Some
analytical Limited
analytical innovative
methods and innovation and Minimal No innovative
methods and methods and methods or
Innovation complex complexity in innovation and
complex moderate complex
and model features the analytical complexity. features
model features complexity in
Complexit are effectively methods and Very basic or applied. No
are applied. model features. meaningful
y applied. model features. incorrect use of
Shows good Utilizes use of
Demonstrates Basic use of PySpark.
understanding PySpark in a PySpark.
advanced use PySpark.
of PySpark. standard way.
of PySpark
capabilities.
Exceptionally
clear and Clear and Poor
Adequate Inconsistent
effective effective presentation;
presentation; presentation;
presentation; presentation; the PySpark
the PySpark the PySpark
the PySpark the PySpark Notebook is No effective
Notebook is Notebook is presentation
Presentati Notebook is Notebook is incomplete or
sufficiently poorly or report.
on and comprehensive well- poorly Presentation
documented. documented.
Report and well- documented. documented. does not cover
Presentation Some parts of key aspects or
documented. Most group Significant gaps
covers major the project are is missing.
All group members in the project
points but lacks unclear or
members contribute scope or
some depth. missing.
contribute meaningfully. process.
meaningfully.
 Excellent
teamwork Good Adequate Inconsistent
dynamics and teamwork teamwork teamwork Poor teamwork
individual dynamics and dynamics and dynamics and dynamics and No perceived
teamwork or
contributions individual individual individual individual
individual
Peer as perceived contributions. contributions. contributions. contributions. contributions.
Review by peers. All Most members Some members Several Significant Major
members are are satisfied have minor members have issues with conflicts or
lack of
highly with each issues with each issues with each teamwork and
participation.
satisfied with other's other's other's contributions.
each other's contributions. contributions. contributions.
contributions.

APPENDIX : Submission Guidelines

Submission Guidelines
Project Report
• Deadline:
23:59, 20-Dec-2024
• File Name Format:
Semester_CS320_Class_FinalProject_Group[GroupNumber].zip
(Example: 242_CS320_01_FinalProject_Group3.zip)

Late Submission Policy