You are on page 1of 2

National University of Sciences & Technology (NUST)

School of Electrical Engineering and Computer Science (SEECS)


Department of Artificial Intelligence and Data Science

Assignment-02 Deliverables
Maximum Marks: 20 Instructor: Dr. Nazia Perwaiz
Date: 2nd October 2023 Due Date: 15th November 2023
Name: Reg No:

Assignment-02

Task-01:

Provide “Project Description” for the project selected by you.

1. Project Title: [Predicting Customer Churn in a Telecommunications Company]

2. Project Objective: [To build a machine learning model that can predict which
customers are most likely to churn (i.e. cancel their subscription) in a
telecommunications company, based on their historical usage data and
demographics.]

3. Data: [The dataset contains information on 10,000 customers of a telecommunications


company. Each row represents a customer and each column represents a feature such
as the customer's age, gender, usage patterns, and account status. The target variable
is whether or not the customer has churned.]

Task-02:

Perform following tasks for your project.

1. Data Exploration and Preprocessing:


a. Load the dataset and examine the columns, their data types, and any missing
values.
b. Check for any outliers and remove them if necessary.
c. Convert any categorical features to numerical features using one-hot encoding
or label encoding.
d. Split the data into training and testing sets.
2. Feature Engineering and Selection:
a. Create new features from the existing features if necessary.
b. Use feature selection techniques such as correlation analysis or recursive
feature elimination to identify the most important features.
3. Model Selection and Training:
a. Choose a machine learning model appropriate for your problem.
b. Train the model on the training set.
c. Evaluate the performance of the model on the testing set using metrics such as
accuracy, precision, recall, and F1-score.

Submission Guidelines:
1. **Report:**
- Prepare a comprehensive report documenting your analysis, including data exploration,
preprocessing, visualization, model building, evaluation, and feature selection.
- Clearly present your findings and conclusions.

2. **Code:**
- Submit the Python code used for the analysis.

3. **Visualization:**
- Include relevant visualizations in your report.

You might also like