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

IOM103 Artificial Intelligence in Business 

Semester 2, 2024/25 Coursework Report 

Submission Deadline: 23:59 on May 15^th, 2025

The coursework aims to provide students with hands-on experience in applying AI techniques to solve real-world business problems. Students will use Python to implement  supervised and unsupervised learning models to analyze data and make business decisions.

The coursework is divided into two parts: Part A focuses on supervised learning and Part B focuses on unsupervised learning. The following content specifies the details of tasks in Part A and Part B.

Part A: Supervised Learning

Task A1: Sales Prediction

Sales prediction is the process of estimating future sales based on historical data, market trends, and other influencing factors. It helps businesses forecast revenue, manage inventory, allocate resources, and make strategic decisions.

For this task, you are required to predict the sales of products using supervised learning models (linear regression, regression trees, and random forests) on the dataset provided by the instructors.

Requirements:

1. Implement different learning models (linear regression, regression trees, and random forest) to predict product sales

2. Compare the performance of the models using appropriate metrics (RMSE)

3. Submit a report that

a) Clearly explains the model development process, choice of the final models, and prediction accuracy

b) Discuss how the predictive results can affect business operations, revenue, and related business performance

4. Submit the Python source code with comments explaining each step (an instruction will be provided)

Task A2: Customer Churn Prediction

Customer churn prediction predicts the likelihood of customers canceling a company’s products or services. In most cases, businesses with repeat clients or clients under subscriptions strive to maintain the customer base. Therefore, it is important to keep track of the customers who cancel their subscription plan and those who continue with the service. This approach requires the organization to know and understand their client’s behavior and the attributes that lead to the risk of the client leaving. The approach is crucial since customer churn is expensive, and acquiring new clients is more expensive than retaining existing ones.

For this task, you are required to do customer churn prediction using supervised learning models (logistic regression, classification trees, and random forests). Creating churn prediction models involves using historical customer data to predict the likelihood of the current customer leaving or continuing with a particular service/product. The dataset will be provided by the instructors.

Requirements:

1. Implement different classification models (logistic regression, classification trees, and random forest) to do customer churn prediction

2. Compare the performance of the models using appropriate metrics (AUROC)

3. Submit a report that

a) Clearly explains the model development process, choice of the final models, and prediction accuracy

b) Discuss how the predictive results can affect customer management, revenue, and related business performance

4. Submit the Python source code with comments explaining each step (an instruction will be provided)

Part B: Unsupervised Learning

Task: Customer Segmentation Analysis

Customer segmentation analysis is the process of dividing a company's customers into distinct groups based on shared characteristics, behaviors, or demographics. It helps businesses tailor their marketing strategies, improve customer experience, and optimize product offerings.

For this task, you are required to perform customer segmentation analysis using unsupervised learning techniques like clustering. The dataset will be provided by the instructors.

Requirements:

1. Develop clustering models to segment customers based on their behaviors and/or demographics.

2. Determine the optimal number of clusters using the Elbow Method or Silhouette Score

3. Submit a report that

a) Clearly explains the clustering process, choice of the number of clusters, and business insights

b) Interpret the clusters and provide business insights (e.g., targeted marketing strategies)

4. Submit the Python code source file with comments explaining each step (an instruction will be provided)

Report guidelines

The final report consists of two major parts: a PDF file that contains all models and discussions and an associated Python file generated by Jupyter notebook with comments explaining each step.

GENERAL INSTRUCTIONS TO CANDIDATES:

This assignment comprises 100 marks and weighs 25% in the final score of this module.

1. The report should be written in English.  

2. Please use the provided report template to produce your report.

3. An electronic version of the report in PDF and a source code file should be submitted. The electronic file and source code file names should be Module Number + “Coursework” + Your Name + Student ID.  

For example: IOM103 Coursework Qian Luo xxxxxx.

4. Standard XJTLU penalties apply for lateness and plagiarism. Please note that weekends are treated as normal working days and count towards the lateness.

HAND-IN REQUIREMENTS:

You should aim to produce a report within 2,000-word counts (excluding table, figures, and code). Marks of up to 5% points will be deducted if you overshoot the word limit.

Please use the following structure to write your report:

· General introduction of your work (5%): Briefly summarize the problems of the project, how you perform the analysis, findings, suggestions, etc.

· Sales Prediction (30%): based on the requirements specified in Task A1 to present your analysis on sales prediction and the associated results.  

· Customer Churn Prediction (30%): based on the requirements specified in Task A2 to present your analysis on predicting customer churn and results.

· Customer Segmentation Analysis (30%): based on the requirements specified in Task B to present your customer segmentation analysis and results.

· Writing style (5%)

You are required to do this project individually. Your assignment markings are graded based on the marking scheme shown on the next page.

Writing tips:

To effectively convey your understanding and illustrate your points:

· Use simple words, short sentences, and short paragraphs.

· Use graphics (such as figures and tables) if applicable, number and name them.

· Use data, examples, and/or cases to support your statements and arguments when it is necessary.

· Use Harvard style for your citation (when applicable).

Marking criteria – Coursework

*** END OF THE ASSIGNMENT PAPER ***