ENG335 Machine Learning Group-Based Assignment July 2025 Presentation | SUSS

Please note the following:  

a) Submission Cut-off Time – Unless otherwise advised, the cut-off time for proposal/interim report submission will be at 23:55 hrs on the day of the deadline. All submission timings will be based on the time recorded by Canvas.  

b) Start Time for Deduction – Students are given a grace period of 12hours. Hence calculation of late submissions of proposal/interim report will begin at 12:00 noon the following day (this applies even if it is a holiday or weekend) after the deadline.  

c) How the Scheme Works – From 12:00 hrs the following day after the deadline, 10 marks will be deducted for each 24-hour block. Submissions that are subject to more than 50 marks deduction will be assigned zero mark. For examples on how the scheme works, please refer to Section 5.2, Para 1.7.3 of the Student Handbook.   

Any extra files, missing appendices or corrections received after the cut-off date will also not be considered in the grading of your proposal/interim report.  

Plagiarism and Collusion   

Plagiarism and collusion are forms of cheating and are not acceptable in any form of a student’s work, including this TMA assignment. You can avoid plagiarism by giving appropriate references when you use other people’s ideas, words or pictures (including diagrams). Refer to the American Psychological Association (APA) Manual if you need reminding about quoting and referencing.  

You can avoid collusion by ensuring that your submission is based on your own individual effort. The electronic submission of your TMA assignment will be screened through plagiarism-detecting software. For more information about plagiarism and cheating, you should refer to the Student Handbook. SUSS takes a tough stance against plagiarism and collusion. Serious cases will normally result in the student being referred to the SUSS Student Disciplinary Group. For other cases, significant marking penalties or expulsion from the course will be imposed.

Group-Based Assignment

This mini-project assignment is worth 15% of the final mark for ENG335 Machine Learning. The total mark assigned to this assignment is 100 marks.  

This is a group-based assignment. You should form a group of a maximum of 5 members from your seminar group. Each group is required to upload a single report to Canvas Turnitin via your respective seminar group. Please elect a group leader. The responsibility of the group leader is to upload the report on behalf of the group. In your 1-page cover sheet, please include all project partners’ names and student PI numbers.  

Note to Students:  You are to submit the GBA assignment i.e. using Canvas in the form of a single MS Word file. It should be saved as ENG335_GBA01_group_number.doc. Submission in any other manner, like hardcopy or any other means, will not be accepted. You are to ensure that the file to be submitted does not exceed 20MB in file size.  

Additional Instructions for Submission:  

Please follow the submission instructions stated below:   

1.  Please submit all Program Code / Answers in the form of a Jupyter Notebook file (i.e. .ipynb File) for all the programming questions via the additional submission link found under Assignments on the ENG335 T01/ T02 course sites.  
2.  All Answers for each question should be indicated clearly using the Comments section/markups in the Notebook so that the marker can see clearly which code is for which Question. (e.g. # Answer for Q1a).   

The cut-off date for this assignment is Saturday, 13 Sept 2025, 23:55 hrs. Late submissions carry a mark penalty.  

Answer all questions. (Total 100 marks)  

Question 1  

(a) Three generative AI applications—GitHub Copilot, Runway Gen-2, and Jasper AI—are available in the market.  

i. For each application, describe one real-world use case in a Singaporean or global industry.  (3 marks)  

ii. Identify one key limitation or risk associated with each tool.  (3 marks)  

iii. Compare any two of the three applications, and argue which is more suitable for a creative versus a technical workflow. Justify your answer.  (4 marks)

(b) Investigate how DeepSeek gained attention and adoption in the market. Using your own understanding and examples, explain why people find it useful or appealing.  (6 marks)  

(c)  After exploring ChatGPT and Perplexity through independent reading and hands-on testing, write a personal comparison of the two. (3 marks)  

(d)  Describe XAI and AGI in terms of Artificial Intelligence and highlight why they are important. Limit your answer to not more than 6 lines for each term. (6 marks)

Question 2  

(a) Perform exploratory data analysis and understand the parameters. Encode the ‘Pop’ and ‘sex’ features. Use 3 for the ‘NA’ values in ‘age’ and 60 for ‘NA’ values in ‘footlgth’. (9 marks)  

(b) The objective is to estimate the possum’s head length. Estimate the possum’s head length using the best FIVE (5) features and present the estimation model.   (10 marks)  

(c)  Assess the performance of the linear regressor by getting the relevant performance metrics. You need to provide any THREE (3) metrics and explain the importance of these metrics. Use at most 15% of the dataset for testing. (6 marks)

Question 3  

(a) Perform exploratory data analysis and understand the dataset. Drop the ‘year’, and ‘species’ features. For ‘island’, use numerical encoding starting from integer 101 for each unique island. Use Python code to discard the data records with missing values. Implement a suitable algorithm from what you have learned in the class for identifying the gender of penguins.  (14 marks)  

(b)  Construct a Naïve Bayes algorithm for the above dataset. (5 marks)

(c)  Use at most 20% of the dataset for testing. Compare the performance metrics of the algorithm in Question 3(a) and the Naïve Bayes classifier. Does the scaling of the parameters have any impact on the performance (Justify your answer)? (6 marks)     

Question 4  

Use the data records only from 14 Jan 2022 to 30 Jun 2024, inclusive of both dates. The objective is to check if the Crude price has any correlation with the other features in the dataset and propose a suitable model to predict the Crude price. Use 20% of the dataset for testing. Your model should use just enough features to have an R2_score of at least 0.70. (25 marks)