As a part of this course, you are required to complete a group lab project of your choice based

on the material of this course. The objective of this project is to enable the students demonstrate

their ability to work as a team in applying data analytic life cycle approach and solve real world

problems using data and analytics.

Project Criteria

Credits: 15% of total grade

Groups: You are required to form groups of 4 for each project.

Project Tasks :

Task I: Group formation, problem identification, and data selection (2 Points)

1. Form your group

2. Select a project identifying a problem in your area of interest

3. Select the required dataset related to your problem. You can select one from

https://www.kaggle.com/datasets or https://www.data.gov.sa or any suitable source

Task 2: Data Preparation (3 Points)

4. You can extract data from images, web, digital documents etc

5. Prepare your dataset for analytic process using appropriate technique that you have

learnt in this course to perform exploratory data analysis and preliminary data

visualization (bag of word, tf-idf, word2vec)

Task 3: Model Planning and Building (5 Points)

6. Identify an appropriate data analytic technique to solve your Problem and justify your

selection

7. Create training and testing dataset

8. Present your results with appropriate visualization technique .

9. write a short intensive report (5-6 pages) to summarize all the steps you followed in your work that contains the following:

Pre- find a title for your project

1.Abstract:

a. briefing why the problem choose is important to be solved,

b. Methodology used to solve the problem,

c. summarize the results and the insights you gained from solving the problem

2. Summarize the Text mining Pipeline steps you followed

3.Dataset Description: describe the dataset you used for solving the problem

4. Data Preparation: Describe the technique used for preprocessing your dataset

5. Model Planning and Building: Describe and Justify the technique used for

solving your problem

6. Result Discussion: discuss the impact of the findings for society/business

The Poster should be displayed in college corridor for presentation and feedback should be

collected for your presentation from at least three faculty members.