QBUS6600 Data Analytics for Business

「文智助手」全场景办公AI助理AI+OPC全流程实践方案(大赛作品) 阅读详情


BUSINESS SCHOOL

Page 1 of 4

QBUS6600

Data Analytics for Business Capstone

Semester 2, 2024

Assignment 1 (individual assignment)

1.

Key information

Required submissions:

? Written report (in pdf, due date: Monday, September 2 by the end of the day).

? Confidentiality Deep Poll online form (deadline for submission: August 19).

Submission instructions for the report will be posted on Canvas in Week 5.

Weight: 30% of your final grade.

Length:

Your written report should have a maximum of 12 pages (single spaced, 11pt). Cover

page, references, and appendix (if any) will not count towards the page limit.

Please keep in

mind that making good use of your audience’s time is an essential business skill: every

sentence, table or figure should serve a purpose.

2.

Problem description

Please start by reading through the Project Outline document for your industry project, which

you can find on the 'Learn about our industry projects' page in the Week 1 module on Canvas.

Focus on the Problem Description section of the Project Outline, especially the first and

the third bullet points (EDA and Strategy), which are the most relevant bullet points for

Assignment 1. Both your analysis and your recommendations should be in line with the

requirements/suggestions provided in the Project Outline.

As a business analyst, you will conduct Exploratory Data Analysis (EDA) of the data

corresponding to your industry project. You should aim to find or reveal all relevant properties,

characteristics, patterns, and statistics hidden in the data, supporting your findings with

insightful plots and relevant statistical output.

Use the results from your EDA to outline a preliminary strategy or provide preliminary

recommendations to the management team corresponding to your selected industry project.

You will have a chance to refine these recommendations in Assignment 2. Please refrain from

extensive modelling and model selection – you will do them in Assignment 2. However, feel

free to fit simple models (e.g., linear regression or logistic regression) for the purposes of EDA

and understanding the relationships among the variables in the dataset.

BUSINESS SCHOOL

Page 2 of 4

3.

Written report

The purpose of the report is to describe, explain, and justify your findings to the management

team corresponding to your selected industry project. You may assume that team members

have training in business analytics, however, they are not experts in statistics or machine

learning. The team’s time is important: please be concise and objective.

Suggested outline for the main parts of the report (further details below):

1. Problem formulation.

2. Data processing.

3. Exploratory Data Analysis (EDA).

4. Conclusions and preliminary recommendations.

You should consider breaking down the longer parts into smaller sections.

4.

Marking Scheme

Business context and problem formulation.

5%

Data processing. 30%

Exploratory Data Analysis (EDA). 45%

Conclusions and preliminary recommendations. 10%

Writing and presentation of the report. 10%

Total 100%

5.

Rubric (basic requirements)

Business context and problem formulation. Your report gives a detailed description of the

problem that is being investigated, providing the context and background for the analysis.

Data processing. You describe the data processing steps clearly and in sufficient detail,

justifying and explaining your choices and decisions. You handle missing values and other

data issues appropriately.

You describe and explain your data transformations and/or your

feature engineering process (if any). Your choices and decisions are justified by data analysis,

domain knowledge, logic, and trial and error (if necessary).

Exploratory data analysis (EDA).

Your report provides a comprehensive description of your

EDA process, presenting selected results.

Your analysis is sufficiently rich, and your

visualizations are insightful. You study key variables and relationships among them using

appropriate plots and descriptive statistics. You note any features of the data that may be

relevant for model building in Assignment 2. You note the presence of outliers and any other

anomalies that can affect the analysis. You explain the relevance of the EDA results to the

underlying business problem and your subsequent recommendations. You clearly describe

and justify the methods in your analysis. The choice of methods is logically related to the

substantive problem, underlying theoretical knowledge, and data analysis. You interpret the

statistical outputs that you provide.

You report crucial assumptions and whether they are

potentially violated.

BUSINESS SCHOOL

Page 3 of 4

Conclusions and recommendations. The reasoning from the analysis and results to your

conclusions and recommendations is logical and convincing. Your conclusions and

recommendations are written in plain language appropriate for non-technical audience.

Writing. Your writing is concise, clear, precise, and free of grammatical and spelling errors.

You use appropriate technical terminology. Your paragraphs and sentences follow a clear logic

and are well connected. If you use an abbreviation or label, you define it first.

Report layout. Your report is well organised and professionally presented, as if it had been

prepared for a client later in your career. There are clear divisions between sections and

paragraphs.

Tables. Your tables are appropriately formatted and have a clear layout. The tables have

informative row and column labels. The tables are relatively easy to understand on their own.

The tables do not contain information which is irrelevant to the discussion in your report. The

tables are placed near the relevant discussion in your report. There is no text around your

tables, and your tables are not images.

Figures (plots). Your figures are easy to understand and have informative titles, captions,

labels, and legends. The figures are well formatted and laid out. The figures are placed near

the relevant discussion in your report. Your figures have appropriate definition and quality.

There is no text around your figures, and your figures are not screenshots.

Numbers. All numerical results are reported to suitable precision (typically no more than three

decimal places, in some cases fewer).

Referencing.

You follow the University of Sydney referencing rules and guidelines.

Python code. The text of your report should be entirely free of Python code.

Note: you are strongly encouraged to use Python for all the steps of your data analysis. While

there is no Python code submission for Assignment 1, you should keep your code well- organized, so that you can easily extend/modify/reuse this code for the purposes of

Assignment 2 (which will have a Python code submission requirement).

6.

Deductions

Marks may also be deducted from each item in the marking scheme in the following cases:

 The report is disorganised and/or has a poor layout.

 There is an excess of abbreviations or labels that the reader may be unfamiliar with.

 The report has an excessive number of grammatical or spelling mistakes.

 The tables are difficult to read, for example, due to poor layout or labelling.

 The figures are difficult to read, for example, due to poor layout or labelling.

 Numbers are not appropriately rounded.

BUSINESS SCHOOL

Page 4 of 4

7.

Late Submission of the report

Late submissions are subject to a deduction of 5% of the maximum mark for each calendar

day after the due date. After ten calendar days late, a mark of zero will be awarded.

8.

Late submission of the Confidentiality Deed Poll online form

It is a requirement of our QBUS6600 unit that all students complete the Confidentiality Deed

Poll online form before gaining access to the datasets for the industry projects. The datasets

are highly confidential, and you have responsibility to keep them secure and only use them

for your QBUS6600 coursework. Submission of the Confidentiality Deed Poll online form

after the August 19 deadline is subject to a penalty of 20% for Assignment 1. Furthermore,

assignments without a submission of the online form will not be marked.
 

船载 OpenHarmony AIS 航海工作台:告警与防碰撞预警系统 船载OpenHarmony AIS航海工作台的告警与防碰撞系统,集成十余类告警(超速、偏航、会遇、SOS等),通过网格空间索引实现高效邻近判定,保障实时性。告警管理器统一调度规则、去重、通知与日志,支持悬浮球、语音、跑马灯、弹窗多渠道触达,确保航行安全。SOS紧急通道独立运行,避免干扰。系统设计强调性能优化与多场景适配,为航海安全提供核心支撑。 阅读详情

相关推荐

AI 应用开发:四维架构落地实战——以 HR Agent 为例拆解感知·推理·记忆·执行【意图路由、规划编排、长期记忆、工具执行、面试题】

本文基于四维架构(感知·推理·记忆·执行),以HR Agent为例,系统拆解大模型应用从“聊天”到“生产可用”的落地路径。通过Spring AI实现意图路由、规划编排、RAG检索与工具调用,结合真实踩坑复盘,揭示架构化设计对安全、成本与可维护性的关键价值,为AI Agent工程化提供可复用的实战框架。

王大师企业官方博客 1325

QBUS6600 Data Analytics for Business Capstone Semester 2 2024 1Python

2024Assignment1individualassignment)•Writtenreport•DeepPollfirstand thethird5%Data30%45%ns.10%report.10%Total•••••。

tolitdentay的博客 634

LLM之RAG实战(五十四)| 复杂文档处理RAG框架:Ragflow

RAGFlow 是一种结合了检索增强(Retrieval-Augmented Generation,RAG)与流程控制(Flow)的人工智能技术架构。它通过检索外部知识库中的信息,结合自然语言生成技术,为用户提供更准确、更丰富的回答。同时,它还引入了流程控制机制,能够根据任务需求动态调整信息检索和生成的流程,从而更好地完成复杂的任务。RAGFlow 的核心优势在于将检索和生成相结合,打破了传统生成模型仅依赖内部参数进行文本生成的局限。

wshzd的博客 1067

AI 问数真的能替代 BI 报表吗?

AI问数赋能自然语言查询,提升临时分析效率,但无法替代传统报表。报表适用于稳定输出与持续监控,AI则擅长探索性提问。企业用好AI问数,关键在于夯实数据模型、统一指标口径、健全权限体系与结果校验机制。合理组合报表、仪表板与AI,才能实现高效、准确的业务洞察。

葡萄城技术团队博客 341

AGX Orin 部署PyTorch与Torchvision 2026避坑指南

本文提供了2026年在AGX Orin开发板上部署PyTorch与Torchvision的详细避坑指南。针对ARM64架构和JetPack 6.2系统,重点解决了Python 3.10环境配置、官方wheel包安装、torchvision源码编译等关键步骤,并分享了常见问题解决方案和性能优化技巧,确保深度学习环境稳定运行。

sky77的博客 753

rk3326 MIPI休眠唤醒黑屏有背光问题

** 1.问题现象: ** **【开机起来】**开机起来可以正常显示 **【按power按键休眠】**第二次按下Power按键进入休眠,隔10s,再按Power按键唤醒。 **【出现结果】**屏幕黑屏有背光,并提示drm time out错 **【lcd信息】**lcd为480*800 2lane的mipi **【复现概率】**第二次按下休眠唤醒必然复现 【具体错误log如下】 //第一次休眠的log// [ 54.858511] dw-mipi-dsi ff450000.dsi: final DSI-

Ian22l的博客 3948

ChatGPT、Perplexity、Gemini 与 AI Overviews 引用对比:谁的引用更可信

AI 引擎的引用机制差异很大:ChatGPT 以行内引用加 Sources 列表呈现来源,Perplexity 几乎逐句可溯源,Gemini 在回答中内嵌相关来源链接,AI Overviews 则把多源聚合答案与来源列表一起放在搜索结果顶部。本文从引用透明度、来源偏好、可干预性 3 个维度对比这 4 个引擎,并给出 GEO 的 3 点启示,帮企业在多引擎环境下提升被引用的概率。

淡然一笑 的专栏 280

图数据挖掘 ECC K-core core number truss number clique

K-core:什么叫k-core,给定一个正整数k(k>=0),k-core是一个G的最大子图(也就是说k-core是一个图的限制),将这个子图定义为Hk,对于Hk中的每个顶点v,他的度数都是大于等于k的。 k-core是内嵌的,如下图所示,集合{ABCD}是H3,也就是3-core的子图。而集合{ABCDE}是H2,也就是2-core的子图,集合{ABCDEGF}是H1,也就是1-core的子图,而从集合的角度来讲H3<H2<H1。 core number:什么叫kcor

weixin_45193103的博客 1687

【从零理解 Spring AI · 12】MCP 的两种角色:做客户端还是做服务端

上一篇讲了 MCP 的概念:标准协议、三大角色、M+N 替代 M×N。

nice_lcj520的博客 616

Windows版MySQL8.4.2LTS解压直用(下载免安装-绿色-项目打包直接使用-含卸载)

安装前运行微软常用运行库全集(也可能称为依赖)关于MySQL8中相关参数配置,可通过。选择8.5.2LTS长期服务版。选中密码,右键会直接复制。

xzzteach的博客 1442

UI自动化控制PC端微信获取当前群聊的群友列表

在一个月前,某个群友在获取整个群的群友信息时遇到了一点问题: 对整个群进行群友数据获取经测试确实有点棘手,下面我将我的解决过程公布给大家。 基础教程详见: https://blog.youkuaiyun.com/as604049322/article/details/121391639 人工打开要抓取的群聊窗口后,首先获取微信窗口并点击聊天信息按钮: import uiautomation as auto auto.uiautomation.SetGlobalSearchTimeout(1) wechatWind

小小明-代码实体的专栏 3万+

抽象主义人工智能和生命体AI的内在联系

彭军辉提出“抽象主义人工智能”作为第四大AI范式,批判符号主义、连接主义、行为主义剥离生命本体的误区,确立“智能是现象,生命是本体”的核心公理。主张原生智能必须依附具备存续诉求的生命本体,提出“生命体AI理论”,构建七层演化阶梯与自闭环工程框架,强调智能不可跳过底层存续机制直接模拟语言。该体系为生成式AI提供科学边界,推动从“仿真表象”向“原生智能”的范式跃迁,开辟硅基人工生命新赛道。

抽象主义人工智能和生命体AI 209

2026AI漫剧放心大胆做!小白也能轻松出片(附保姆级教程)

要是在2025,我大概率会劝他再等等,毕竟那时工具还没这么顺手。但到了2026年的今天,我的回答得很干脆:放心去做,绝对没问题。这一年多来,AI漫剧这块的变化真可谓翻天覆地。过去你想拍个像样的短片,哪怕再简陋,也得凑齐拍摄设备、找场地、找演员,后期剪辑更是折磨。但现在,时代变了,AI已经把创作的门槛踏平了。你不需要请演员,也不用操心灯光布景,更不用为剪辑特效烧钱。一个人,一台电脑,花几天时间就能做一部完整的AI漫剧。你只要有有想表达的故事,突发的灵感,剩下的,都能直接交给AI落地。

欢迎来到鸾姝淡月博客,专为程序员和编程爱好者打造的技术博客。我们分享编程语言趋势、开发工具、编程哲学、职业发展等,助你掌握新技术,优化技能,激发编程热情。 601

OpenAI Control Room 架构拆解:给企业 AI Agent 加一套可审计的急停系统

OpenAI 公开了用于追踪和停止研究模型工作负载的 Control Room。本文拆解 job_id、推理前鉴权、35 秒撤销窗口与 Fail Closed 设计,并给出企业 AI Agent 急停控制面的数据模型、FastAPI 参考实现、缓存撤销策略和故障演练清单。

jerry764的博客 345

【ESP32设备通信】-LoRa通信

在本文中,我们将使用 Arduino IDE 将 ESP32 与 LoRa SX1278 (Ra-02) 模块连接起来。 我们将创建一个真实的示例项目,通过 LoRa 无线打开/关闭 LED 进行演示。

视觉与物联智能 1894

jre9下载 jdk9

(Java SE Runtime Environment 9.0) 9.0u175 官方最新版 【x86|x64】

OpenClaw 深度调查:把 AI 助手做成你自己的控制平面

对 openclaw/openclaw 的完整技术尽调:Gateway 架构、Agent 运行时、工具与沙箱、30 个消息通道、181 个插件、安全信任边界、工程代价与采用建议。17 章 / 10 张图,全部数字标注口径,数据截至 2026-10-31。

厚积薄发 363

假人有限元模型

假人模型,车辆碰撞假人有限元模型,适合做乘员安全的研究者利用

AI赋能智慧港口建设|造形家快速生成港口全要素三维场景

随着智慧港口、港口数字孪生项目的持续推进,港口三维场景的需求日益旺盛。传统港口三维建模,往往需要航拍倾斜摄影采集数据,再人工搭建吊机、岸桥、船舶、集装箱等大量工业设施模型,项目周期长、人力成本高,修改迭代繁琐,制约港口可视化项目落地效率。国产AI三维建模工具,依托卫星影像 AI 识别能力,无需航拍作业,一键快速搭建港口完整三维场景,为港口数字孪生、方案汇报、投标演示提供高效的场景解决方案。

m0_69539167的博客 87

老版QQ原生表情gif动态

这是老版的QQ表情,不过全是动态的的,Windows照片查看器是不会动的,可以右击用浏览器打开查看,再说一遍是老版的,只是分享给宁愿用老版也要动态的人。

从设备增点到治理闭环:老旧小区物业数智化落地实践

系统连接合同审批、银行流水、收费记录与项目台账,执行到期提醒、收入核验、异常标色和月度对账,让每一笔资金来源明确、去向可查。针对设施老旧、诉求响应慢、公共收益不透明等问题,津南以6类小区为试点场景,统一建设物业数字化底座,关联楼栋、单元、房屋、业主、空间、设施设备、工单、公共收益等核心数据。系统采用统一编码管理,将摄像头、路灯、井盖、道路、绿化等设施纳入资产台账,解决纸质记录更新滞后、故障责任难追溯的问题。基于历史工单建立分类模型和知识库,辅助识别照明、给排水、电梯、环境秩序、秩序维护等问题;

wuyeshuzhihua的博客 163

企业微信iPad协议详解:接口接入、实时消息同步与语音转码实践

深入解析企业微信iPad协议的技术架构与开发思路,涵盖API接口接入、长连接通信、实时消息同步、Silk语音转码、异常重连及高并发优化,帮助开发者了解企业微信自动化系统的设计与实现。

欢迎来到祖安! 514

Product Hunt 热榜 2026-11-13:Plurai Simulation、YouArt Desktop App、Omnigraph

2026-11-13 Product Hunt 新产品精选:Plurai Simulation、YouArt Desktop App、Omnigraph。汇总 15 款产品的中文介绍、功能关键词和产品链接。

LaughingZhu的博客 619

【AI Agent面试系列】AI Agent可观测、评测、安全相关的知识点

之前的文章介绍了和,本文主要介绍AI Agent的测评、可观测等知识。

408

Docling 原理解读:是什么、为什么、怎么样

从论文视角拆解 Docling 的整体架构、DoclingDocument 数据模型、PDF 预处理、版面分析、OCR、TableFormer 双解码器、阅读顺序与装配流程,并解释版面框与 OCR 框的区别。

PLANTTHESON的博客 402

WorkBuddy 实战:一句话需求 → 七屏可交互原型,户外徒步 App 的 AI 设计全流程

WorkBuddy 实战:一句话需求 → 七屏可交互原型,户外徒步 App 的 AI 设计全流程,跟着博主一起来还原整个过程。

夜郎King的博客 5167

从认识人工智能到理解机器学习:我的 AI 入门第一课

正式开始学习人工智能之前,我对 AI 的认识其实比较模糊:知道 ChatGPT、知道大模型,也知道现在很多岗位都在谈 AI,但如果有人问我“人工智能到底是什么”“机器是怎么学会识别一只猫的”,我未必能从头到尾讲清楚。上午的课程更偏向行业全景:人工智能的发展、研究方向、NLP、岗位分工、学习路线和 AI Coding 工具。下午的课程更偏向技术基础:机器学习的原理、有监督学习、深度学习、模型训练和评估方法。

chh563的博客 573

企业宣传片发前如何批量排查并遮挡视频里的敏感信息

做企业视频的人都会碰到一个具体问题:实拍画面里混进了不该出现的信息。办公室背景里有贴着客户信息的白板,采访对象的授权书边缘露出一串身份证号码,街采素材里路人面孔和车牌号直接入镜。人眼在时间线上扫视,会漏掉快速闪过的帧、画面边缘的小字、以及暗光区域里的证件号码。用抹影AI完成车牌、人脸和证件区域批量检测后,又手动补充了两个时间段的屏幕遮罩,最终导出时画面已无合规隐患。重点关注快速运动、遮挡、低光照条件下的目标,这些是漏检的高发区域。导入视频后选择要检测的目标类型(人脸、车牌、证件号、二维码等)。

Mysssone的博客 182

面向工业对讲的双通道声学 DSP 模组 A-59(NR2050-A)方案解析与工程落地案例

A-59模组以NR2050-A DSP为核心,37.5×16mm邮票孔封装,支持-40℃~85℃工业温域,兼容A-06/A-09/A-29系列,可低成本替换存量设备。通过固件切换实现三种模式:模式一(低改版成本,适配矿井、电梯);模式二(最优AEC,用于医院呼叫);模式三(双波束独立输出,支持双人会议语音分离)。集成AEC、ENC、BF与AGC算法,有效抑制回声、噪声与串扰,解决对讲系统核心声学难题。选型需注意参考信号路径、麦间距与温度匹配,建议先做声学测试再量产。

R190_6589的博客 374
上一篇: INFS6071 Critical Path Analysis
下一篇: Project 1: Specification for Automail
vx_codinghelp
博客等级 码龄2年 543粉丝 68原创
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付:10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值