Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

Term project 1

AFL Sports Fans’ Love of Their Team and Its Impact

The sport industry plays a major part in the lives of people, whether they are participants or spectators and is of immense and growing economic importance. It is part of the entertainment industry and deserves more research attention. It has high and growing economic importance with an estimated value of $1.3 trillion globally (www.plunkettresearch.com/statistics/Industry-Statistics-Sports-Industry-Statistic-and-Market-Size-Overview/ ). It occupies a substantial amount of people’s time. It is an important focus of technical innovations, with technical advances in the way sporting events are run, covered, analysed, visualized and communicated to consumers who are increasingly mobile and digitally connected. It plays a major part in the social and cultural life of people. And other industries can learn from the way   the sports industry operates.

A fan’s love of their team can take on more extreme forms than typically exist in other types of consumer-brand relations. The relation between a fan and their sports team has been described as a type of fanaticism, a religious fervor that defines them and continues over a person’s lifetime. It can be seen as a type of marriage between the fan and the team, to honour the team, to have and to hold in sickness and in health  (when the team is doing well and when it is not), remain loyal and forsake others ‘til death do us part’ .

This term project is focused on studying the sports team fan. We have run a survey among Sydney Swans’ fans (https://www.sydneyswans.com.au/) and the data set has been posted on Canvas. Your task is to investigate the sports team fans’ love to a team and the impact on the club’s business performance (e.g., game attendance (Q1_7) and season pass renew intention (Q14_6)).

This assessment will test your knowledge and ability in analysing quantitative data by using a variety of methods learned in class.

You will be required to use various machine learning techniques to analyse the data provided.

(1)     First of all, you need to get yourselves familiar with the corresponding data.

Please go through the data description carefully. What information has been collected in the data? What does each variable (column) represent? You need to clean up the data before actual analysis.

(2)     Secondly, think about what are the questions you want to answer in order to  achieve the project objective: improve Sydney Swan’s business performance. What questions can be answered by using the data collected? List all the questions that you want to answer AND questions that can be answered by the survey data.

(3)     Thirdly, choose a specific test to answer each of the questions you have listed. You have to use each of the following ML techniques at least once in the assignment:

Logit Model

Random Forests

Gradient Boosting

Support Vector Machines (SVM)

You’re free to use other necessary techniques learned in/outside this course (e.g., descriptive statistics, tabulation, recommender systems). For each question, you will need to specify what test(s) was (were) used and what information from the survey e.g. question(s)/variable(s) was used?

(4)     Next, for each specific test conducted, interpret the results and transform the

results into words (findings) i.e. based on your results, what further information and recommendations (e.g. managerial actions) can you provide to the national and store brands?

(5)     Finally, overall recommendations based on all previous analyses. What are the limitations (if)? Do you need further research?

Submission Instructions:

1.      This is a team assignment and your answers are to be typed with appropriate outputs shown (as appendices and cited accordingly in the report). When writing up your report, please use Microsoft Word.

2.      It is critical to be able to present your results succinctly and with clarity at all times. It is aimed that through this assessment, we can appreciate the utility of ML techniques as well as creating an avenue to train our reporting styles in the market machine learning arena. A brief literature would be a good starting point. A table of contents would be also useful for your report. Please use your discretion to structure your write-up in a professional and logical manner.

3.      The report should not exceed 1,500 words excluding appendices. It should be professionally presented with standard formatting (e.g. font 12, 1.5 spacing, 2.5cm/1inch margin throughout etc.). Please use Harvard referencing in your report.

4.      You are required to submit a softcopy of your report (including your Python codes & output  and data files) on Canvas by its due date/time.

5. Peer Evaluation Forms MUST also be submitted individually, otherwise your results can’t be released.

Marking Criteria:

Marks awarded will be based on the following:

1.      Good understanding of issues (questions) you want to address.

2.      The appropriate application of ML techniques using the “right” measures/variables.

3.      Provision of appropriate analysis citing relevant Python outputs as evidences to your findings.

4.      Ability to apply and communicate results in context of the research questions/issues highlighted.

5.      Overall professional presentation of written work; e.g. Layout, grammar,

integration of results & findings, clarity of recommendations etc.