在作业 1 中，你需要为你的提议系统撰写一份设计报告，阐述你的想法、它所解决的问题以及你计划如何用你的系统解决这个问题。作业 1 不要求你实现该系统。然而，在作业 3 中，你需要使用 R 对你的数据集进行探索性数据分析 (EDA)，以证明你的项目的可行性。作业 3 不强制要求你完全实现提议的系统，但你应该详细描述你的分析或模型的整个过程、方法和预期结果。

Here is the clarification regarding Assignment 1 & 3.

If needed, we will update this post to keep you informed, so please check it regularly.

• The meaning of novelty:

For novelty, you can present a new idea based on existing studies such as proposing a new approach, using new data, applying new ML algorithms, introducing new analytical methods or offering new insights. Your project meets the novelty requirement as long as it introduces something unique or improves upon existing methods.

• The range of topics:

As mentioned in the assignment specification, the proposed project should align with the following business scenarios: agriculture, education, finance, gaming industry, healthcare, social media, and sports.

• Tables and images in Assignment 1

Including tables and images is not mandatory; however, if you believe they would enhance your submission and help explain your points more clearly, you are welcome to include them.

• Including Tables and Images in Assignment 1 (PDF and Google Form)

If your PDF proposal includes images and tables, please submit it as is on Moodle. However, since images and tables cannot be uploaded to the Google Form, copy and paste only the text of your proposal into the Google Form.

For the peer grading, you will receive 6 PDF proposals from your peers via email.

• Google form

You can access the google form in the assignment specification or please use the following link as well.

https://forms.gle/ME3wRyaQxK9LKgNy7

• Am I required to develop and implement my proposed model and system for Assignment 3?

No, you are not required to implement the model or system that you propose for Assignment 3. Instead, you need to submit a report that outlines your proposed model/system, explaining your idea, the problem it addresses, and how your model/system would solve this problem.

For Assignment 3, you are required to conduct exploratory data analysis (EDA) on your dataset using R to demonstrate the feasibility of your project. A full implementation of the proposed model/system is not mandatory. However, you should provide a detailed description of the overall process, methodology, and the expected outcomes of your analysis, model, or system.

• Format requirements:

No specific format is required but I can suggest some general formatting as follows:

- Font: Times New Roman or Arial

- Font Size: 12-point

- Line Spacing: Single-spacing

- Alignment: Justify (except for the title, which may be centered)

- Indentation: First line of each paragraph indented

- Referencing style: APA 7th (https://www.monash.edu/library/help/citing-and-referencing)

• Word limit:

Word limit excludes Cover Page, Table of Contents and References. (Note: Including a cover page and table of contents is optional.)

封面应该遵循什么格式

标题、单位名称和您的姓名就足够了。

字数限制不包括封面、目录和参考文献。请确保遵守规定的字数限制。+- 5% 是可以接受的

• 提案 1 没有特定的模板。您应该根据作业规范中概述的作业要求撰写提案。 • • 正如任务说明书中提到的，拟议项目应符合以下业务场景：农业、教育、金融、游戏行业、医疗保健、社交媒体和体育。 • • 很遗憾，Google 表单无法上传图片。请仅复制并粘贴提案文本到表单中，并确保在提交前进行校对和最终定稿。

是的，请将整个提案复制并粘贴到 Google 表单中。如果您发现任何图片和表格，请添加说明，但请不要添加图片和表格，因为它们无法添加到 Google 表单中。

是的，你可以在作业 3 中使用生成的数据集进行演示。但是，请确保生成的数据集真实可靠，并基于清晰的假设或来源，以与你的主题相关。此外，详细说明你如何生成数据集以及你使用的 GenAI 工具也很重要。确保在你的报告中明确提及使用 GenAI 生成数据集。这种方法将有助于证明你的项目的可行性和潜在有效性。

如果你的提案中所有内容都是你自己的想法，而不是基于任何外部来源，那么参考文献并非严格要求。然而，大多数情况下，学生会参考一些背景文献或数据集来增强提案的可行性和可信度，因此添加参考文献通常是必要的，并且也需要用来支持你的想法。

APA 7格式使用参考文献

This data science project is any project that uses data to solve a real-world problem in a novel way. It does not necessarily need to be highly sophisticated or require advanced AI algorithms. The key points are:数据科学项目是指任何以新颖方式利用数据解决现实问题的项目。它不一定需要高度复杂或需要先进的人工智能算法。关键点如下：

• Problem significance: The project should address a real-world issue in one of the suggested areas (e.g., healthcare, education, sports, gaming, finance, social media, agriculture) and demonstrate potential impact.问题意义：项目应解决建议领域之一（例如医疗保健、教育、体育、游戏、金融、社交媒体、农业）中的现实问题并展示潜在影响。
• Novelty: It should introduce something new—this could be a novel approach, applying existing techniques in a new context, or addressing an underexplored problem.新颖性：它应该引入一些新的东西——这可能是一种新颖的方法，在新的环境中应用现有技术，或者解决一个尚未充分探索的问题。
• Data-driven approach: You need to collect or use data, process it, and draw insights for A3. 数据驱动方法：您需要收集或使用数据，处理数据，并为 A3 得出见解。
• Scope / scale: The project should be manageable within the assignment limits (up to 1000 words for the proposal). You don’t need to handle massive datasets or highly complex models, but it should clearly demonstrate your ability to define a problem, identify relevant data, apply suitable methodologies, and analyze results.范围/规模：项目应在作业要求的范围内可管理（提案最多1000字）。您无需处理海量数据集或高度复杂的模型，但应清晰地展现您定义问题、识别相关数据、应用合适方法并分析结果的能力。