Reference no: EM133740653

Machine Learning in Business

Learning Outcome 1: Analyse and frame business challenges using machine learning concepts, techniques, and the machine learning model development lifecycle.

Learning Outcome 2: Select and apply appropriate machine learning techniques to solve business problems and evaluate the machine learning model performance.

Assessment Task - Case Study (Business Report)

Description

Purpose
This task provides you with opportunities to learn supervised machine learning and Python skills (GLO1 & ULO1) and apply your digital literacy to research and develop a machine learning solution (GLO3, GLO5, and ULO2). By completing this task, you will gain knowledge and skills in selecting and applying one or more appropriate supervised machine learning algorithm(s) to develop and evaluate a machine learning solution and present and interpret the outcomes to business clients.

Case Study

Assignment 1 involves a consulting project with your client - Play Quest Conquer (PQC), an online gaming platform headquartered in Sydney, Australia, offering services globally. PQC boasts a diverse collection of online games. Users sign up and pay a monthly subscription fee to access their services. They can browse games, select what they like, and pay for them. The games they purchase will be added to the user's individual collection to 'own' and play, invite other users to play together, or even 'trade' games with each other. Moreover, users can mark certain games as 'Interest' or 'High Interest' indicating their level of interest to be invited by game owners.

The client's primary objective is to determine the factors influencing game ratings, which will inform their game development, acquisition, deployment, and promotion strategies. You are provided with a dataset acquired by PQC's market research team. Read the PQC Metadata for the description of the columns in the dataset. You are required to estimate Average_Ratings.

The client's specific objectives include extracting insights from the data, estimating game ratings, and identifying opportunities/strategies for improving user satisfaction and game acquisition.

Regarding the extraction of data insights, PQC has requested the following analyses as a starting point:
General information and game configuration: Summarise the kind of games in the dataset, in terms of game types, year of release, age category, minimum number of players required, and maximum number of players allowed.
Game engagement: Summarise the average play time? Are there outliers?
Game engagement and rating: Is there a relationship between the playing time and the average ratings?
Game complexity and rating: Is there a relationship between level of game complexity and the average ratings?

How do game configuration, popularity and Interest (e.g., minimum number of players required, maximum number of players allowed, and number of owners, number of traders, numbers of interests and high interests) correlate with rating? For example, are games purchased by more users likely to result in higher ratings?
Additional insights regarding data quality, other variables and relationships.

You are required to explore this dataset and develop and test a machine learning model(s) using Python. You are also required to report findings to Ms. Anita Craig, Market Research Manager, Play Quest Conquer.

Challenge: You are also supplied with a second dataset without labels: PQC_competion.csv You are invited to apply the model on this second dataset. The model with the best performance will win a small prize!

The dataset used in A1 has been developed based on an external dataset. The dataset then has undergone further pre-processing and resampling specifically for the purpose of learning. Therefore, it is important to note that the dataset may not accurately represent real-world scenarios. It is essential that your insights and conclusions are justified based on the provided dataset. The source of the dataset will be provided upon request after the assignment has been returned.

Specific Requirements
You are required to:
Develop your business and data understanding.
Prepare and explore the provided dataset, cleanse and pre-process data as needed.
Undertake machine learning model development and evaluation.
Report findings to Ms. Anita Craig, Market Research Manager, Play Quest Conquer.
Format and present your report professionally. Two sample report templates are provided under Assessment Resources.
Correctly use the APA7 style of referencing.

Part 1. Business Report (PDF and Word files)
A cover page (not included in the word count) that includes:
Report Title
Unit code and name
Student name and student ID
A table of contents (not included in the word count)
An executive summary of max. 200 words is required (included in the word count).

The report should include:
Business understandings including the business problem to address and other Business Analysis Core Concept Model (BACCM) elements in relation the case study.
Data understanding, data preparation, exploration, visualization, and insights gained.
The machine learning approach undertaken.
The model and performance metrics.
Discussion of the pros and cons of the model.
Business solution and recommendations for implementation and improvement (based on the model).
References using the APA7 style (not included in the word count)

Part 2. Python notebook

The final submission should be presented professionally. The report should use clear, concise, and relevant language to communicate the content to the target audience.

You should research to solve the business problem. In the end, you must exercise and understand the Python code yourself for your learning purposes, develop and present your business understandings and solution to the client. Cite and reference any sources you use.