Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 2

Department of Mathematics

Course Title Machine Learning Course Instructor Dr. Israr

Task Title Semester Project Task Description Classification and


Regression

Dataset Link: House Price Prediction

Objective:
This semester's project aims to develop a machine-learning model for predicting house prices
based on a given dataset. Additionally, students will explore the classification aspect of the
dataset to categorize houses into different classes or labels based on certain criteria. You have
to add a new column to the dataset containing price categories. For this purpose, you have to
put pressure on your mathematician head to figure out the price categories based on the price
values column.
Tasks:
1. Data Preprocessing:
● Explore and understand the dataset.
● Handle missing values, outliers, and any other data-cleaning tasks as discussed in the
tutorial and practiced in Assignment 1.
● You can also perform some analysis to gain insights into the relationship among
attributes and the relationship of any attribute to the class label.
(Hint: covariance, count of class label based upon attribute values, etc.)
2. Regression:
● In this project, you have to work with both train and test files in the dataset.
● Build a regression model to predict house prices based on relevant features.
● Evaluate the model's performance using appropriate metrics (e.g., Mean Squared
Error, R-squared).
● Fine-tune the model parameters for better performance.
● Test your trained model on the test file of the dataset.

3. Classification:
● Identify the categories for converting price values into appropriate categories such
that the current regression problem becomes a classification problem.
● Preprocess the data for classification, including encoding categorical variables.
● Apply the different classification models you learned in the class to categorize houses.
● Evaluate and compare the classification of these models using appropriate metrics
(e.g., accuracy, precision, recall).
4. Combined Analysis:
● Explore the relationship between house prices and the identified classes.
● Analyze how certain features contribute to the classification of houses.
● Visualize the results to present a comprehensive analysis.
Submission: (Week-15)
Students are required to submit a comprehensive report that includes:
● Data preprocessing steps.
● Regression model development and evaluation.
● Classification model development and evaluation.
● Analysis and interpretation of results.
● Visualization of key findings.

Presentation:
You are required to present your work in Week 15/Week 16.

You might also like