Files to be submitted (as one .zip file):

1. Dataset

2. Python program (.ipynb) to solve a Kaggle competition

(https://www.kaggle.com/competitions)

3. Written report (1,000-3,000 words, Calibri, font size 12) in PDF format

Name your .zip file:

Please use the initial letters of the Pinyin of each character in your name_your student   number_your undergraduate major. For example, Chen Dawen should name his .zip file as CDW_23888888_Statistics.zip.

Also, submit your PDF report togo through Turnitin:

Please name your PDF report the same as your .zip file, and submit it through the “ Project Report” link.

Expected structure of the report:

•    Description (of both dataset and research question)

•    Methodology and rationale

• Results

•    Interpretation

•   Conclusion, with

• Visualization

Submission deadline:

11:59 PM, 3 Dec 2023 (Sun). Late submission will result in a 0 mark.

Marking scheme:

•    Research question and methodology (30%)

•    Notebook with clear code and comments (30%)

•   Writing (40%)

Important:

Plagiarism is strictly forbidden. Submitted report will undergo a plagiarism check to

ensure that it is not copied from other sources or generated by an AI system. If caught, the course will be graded as Fail.

Datasets chosen by previous students:

Airbnb New User Bookings

Digit Recognizer

Santander Customer Transaction Prediction

IEEE-CIS Fraud Detection

Predict Future Sales

LANL Earthquake Prediction

Titanic - Machine Learning from Disaster

Google Brain - Ventilator Pressure Prediction

Rossmann Store Sales

San Francisco Crime Classification

Restaurant Revenue Prediction

Stay Alert! The Ford Challenge

Boston Housing

Data Science London + Scikit-learn

House Prices - Advanced Regression Techniques

Mental Health in Tech Survey