BNU-HKBU United International College
DS 4013: Data Mining (For DS students)
Fall 2020 Course Project 1: Classification Analysis

Description:
This is an individual project related to classification analysis. The goal is to create an
accurate classifier and make prediction on unseen records.

Submission Requirement:
Upon completion, each student must submit the following materials:
1. Test data and its prediction
2. Code
a) You MUST implement the following models by yourself: KNN, Naïve Bayes and
Perceptron.
b) You MUST adopt at least two models besides the aforementioned three ones
for your classification task. You do not need to implement by yourself, instead
you can take advantage of open source libraries, for example scikit-learn.
c) Your code must be executable without any bug and can read the test data to
perform prediction and report the performance. Include a README file to
introduce the information for your code and explain how to execute your code.
3. Implementation report
In the report, the following components should be included:
1. The workflow.
2. The models adopted (your implementation as well as those provided by
existing libraries )
3. Experimental results of different models, e.g., Macro-averaging/Micro-
averaging of precision/recall/F-score.
4. Result analysis
a) Which model achieves the BEST performance on this dataset? Why?
b) Conduct error analysis for the models that do not perform well.

Assessment:
1. Classifier implementation and performance: 70%
2. Code: 10%
3. Project report: 20%
4. Bonus: 10%
a) Novel strategy that improves the classifier performance, e.g., ensemble
learning, data preprocessing methods, etc.
b) Implementation of other models by yourself.

欢迎咨询51作业君