Hello, if you have any need, please feel free to consult us, this is my wechat: wx91due

SCHOOL OF COMPUTER SCIENCE

MASTER OF APPLIED COMPUTING (MAC)

ASSIGNMENT 2 (Weightage 15%)

SEPTEMBER 2024 SEMESTER (Block 2)

Scenario and Task Description

In industries where competition is high and profit margins are low, satisfied and loyal customers can distinguish organizations from their competitors, providing a competitive edge and the potential for greater profits. Research frequently demonstrates that organizations benefit from satisfied and loyal customers, but the factors that contribute to satisfaction and loyalty are not always clear in ways that can be translated to action for practitioners. Prior airline industry studies have revealed that customer satisfaction leads to higher profits and encourages loyalty behaviors. For example, satisfied airline customers are more likely to recommend an airline and repurchase tickets (Kim and Lee, 2011), which contributes to an airline's profitability and increased market share (Buttle, 1996; Dagger et al., 2007; Devlin and Dong, 1994). Additionally, loyal consumers are more willing to forgive a service failure and are more resilient to rising prices (Mattila, 2001).

Global Aviation Analytics Market show an increasing trends by year of 2027.

Data analytics for an airline passenger satisfaction study typically involves gathering, processing, analyzing, and interpreting data related to the experience of passengers across different dimensions. This process helps airlines understand key drivers of satisfaction, identify areas for improvement, and optimize services

Practical Skills

Perform exploratory data analysis and build a predictive model that answers the question: “Passenger satisfied or not satisfied with the airline services” based on the factors identified in the airlinesatisfaction.csv dataset. Write a python program to answer the following.

However, before the prediction can be made this dataset needs to be pre-processed before it can be fed into AI prediction model. Pre-process the airlinesatisfaction.csv dataset with Python programming on Google Colab. Each question below required your code.

1. A.I. systems are trained on patterns in certain examples, and because all possible examples cannot be covered, the systems are easily confused when presented with a new scenario. Airline schedules are easily changing every day due to weather condition, technology difficulties and many more reasons. How can AI handle this mistake? (1 mark)

2. Loading dataset into a Pandas DataFrame and list the libraries you may need to use. Find the following information: (3 marks)

a. Number of rows and columns

b. Find the basic statistics of all columns and listing the basic information of the columns- find out the data type for each column

3. Identify how many attributes contains missing values. Handle the missing values. Find number of missing values from each attribute and handle them. You may use imputation. Explain your method. (2 marks)

4. Identify 2 main variables that can show high relationship with the target variable in detecting the passenger satisfaction? Plot a heatmap to explore the relationship between them. (3 marks)

5. The target variable (satisfaction) has 3 values (satisfied, neutral, dissatisfied). Change the values into binary classification. Show your code and count how many of them from both new values. (3 marks)

6. Create a single train/test split of the data. Set aside 80% for training, and 20% for testing. Create a

Neural Network Modelling and fit it to your training data. Measure the accuracy of the resulting Neural Network model using your test data. (3 marks)

Submission Requirements

1. Font type : Times New Roman

2. Font size : 12

3. Line spacing : 1.5

4. Alignment : Justify Text

5. Document type : .pdf, .ipynb

6. Number of pages : 5 – 12 pages (do not exceed the page limit)

7. Your full report should consist of the following:

a) Cover page (Name, ID, Date, Signature, Score)

b) Marking Rubrics & Declaration (attach as second page in the report)

c) Report of your answer script

d) Appendixes (line spacing = 1.0)

· List of references (APA format)

· Python script

· Report of similarity score (percentage of similarity score from each source needs to be shown)

8. Start each question on a separate page.

9. All figures and tables are labelled properly.

10. File naming conventions: StudentName_Assignment1