King's University College Fall 2024 MOS 1033A Introduction To Business Analytics PDF

King's University College Fall 2024 MOS 1033A...

King's University College Fall 2024 MOS 1033A SPECIFY THE QUESTION: USING BUSINESS INTRODUCTION TO BUSINESS ANALYTICS TO ADDRESS ANALYTICS BUSINESS QUESTIONS PART I: INTRODUCTION AND SPECIFY THE QUESTION CHAPTER 1 © M cG ra w H ill L L C. A ll rig h ts re s e rv e d. N o re p ro d u ctio n o r d is trib u tio n w ith o u t th e p rio r w ritte n co n s e n t o f M cG ra w H ill L L C. 1 2 1.1 Define a business process and BUSINESS VALUE AND BUSINESS PROCESSES explain why increased data availability has given rise to the role of business Business value refers to all the items, events, and interactions that analyst. determine a company’s financial health A business process is a coordinated, standardized set of activities conducted 1.2 Differentiate between data and by both people and equipment to accomplish a specific business task information. Companies perform thousands, and sometimes millions, of 1.3 Summarize the role of the business processes each day to create business value analyst. CHAPTER Examples include: OVERVIEW 1.4 Describe how business functions DoorDash pays its drivers, who are independent contractors, for use business analytics. making deliveries Tesla produces an electric vehicle to sell in China 1.5 Identify the components of the SOAR analytics model. Procter & Gamble (P&G) addresses customer complaints, sometimes by giving refunds ALL of these process make DATA! (measures something!) 3 Watch the video: 1 Domino’s Drives Innovation With Data 3 5 Professor J. Siambanopoulos 1 King's University College Fall 2024 MOS 1033A THE DATA ANALYST THE INCREASING AVAILABILITY OF DATA Data analysts are known to work with large data sets to identify patterns and trends, which can be used to inform business decisions. They use statistical tools, techniques, and programming languages like SQL and Python to collect, clean, transform, and analyze data. Some common responsibilities of a data analyst include: Collecting data from various sources Cleaning and organizing large dataset Manipulating data for Exploratory Data Analysis Performing statistical analysis and data mining EXHIBIT 1.1 Data Growth Since 2010 Source: IDC Global DataSphere, November 2018, p. 6, https://www.seagate.com/files/www- content/our -story/trends/files/idc-seagate -dataage-whitepaper.pdf (accessed July 3, 2019) Creating visualizations and reports to present findings Identifying patterns and trends in datasets Watch the Extra video: 2 Big Data Explanation and Examples 6 https://www.datacamp.com/blog/data-analyst-vs-business-analyst 6 7 THE BUSINESS ANALYST THE ROLE OF THE BUSINESS ANALYST A business analyst is a data specialist who curates and uses data Decision Maker – Needs Knowledge and Information to Make to help an organization make effective business decisions Decisions Some common responsibilities of a business analyst include: Business/Data Analyst – The Interpreter/Connector. The one that Identifying and defining business needs knows business, knows what data is needed, and knows how to Gathering, analyzing, and interpreting data communicate with both the decision maker and the data scientist Evaluating current processes and identifying areas for improvement Developing solutions to business problems Data Scientist – a specialist who knows how to work with, Creating reports and visualizations to communicate insight manipulate, and statistically test data “Use data to make business decisions” Watch the video: 3 What does a Business Analyst Actually Do https://www.datacamp.com/blog/data-analyst-vs-business-analyst 8 8 9 Professor J. Siambanopoulos 2 King's University College Fall 2024 MOS 1033A WHAT DOES A BUSINESS ANALYST DO? DATA HELPS AND HINDERS THE ANALYST ROLE Helps: More Data = More Data-derived Insights for Decision Making Their job: Hinders: The increasing amount of data may hinder the work of the analyst through data overload, where too much data may not be properly synthesized or interpreted 12 10 12 AN ANALYTICS MINDSET An attitude, a way of thinking, or a frame of mind An analytics mindset is a way of thinking that centres on the correct use of data and analysis for decision making ”Here’s my problem, what data do I need, how do I get it….” According to EY, an analytics mindset is the ability to Ask the right questions “Prompt Engineer” Extract, transform, and load relevant data (knowing WHAT data and HOW to obtain it) Apply appropriate data analytic techniques (knowing the RIGHT way to analyze, or how to get the help to do that) Interpret and share the results (how to report) These are ALL becoming BUSINESS skills (not just tech skills) 13 14 13 14 Professor J. Siambanopoulos 3 King's University College Fall 2024 MOS 1033A INFORMATION VALUE CHAIN INFORMATION VALUE CHAIN (EXAMPLE FOR TIDE PODS) Data – Data Dump of Instagram Posts (collect ALL posts with any reference to “Tide Pods” or related) Get as much info as possible about the posters of those posts or commenters (this will help the next step) Context – Instagram Posts regarding Tide (detergent) Pods from people who wash clothes (parents, etc.) Data - Raw Facts that have Little Meaning on their Own What is the profile? Background (what is common in these?) With Context – The Setting, Event, Statement or Situation Information – Current Level of Consumer Sentiment Regarding Information - Data Organized in a Way to Be Useful to the Analyst Tide Pods (positive vs. negative posts, popular themes, prevalent or User Combining Data with Context opinions, what do the majority think?) Knowledge – Understanding or Familiarity With Information Gained Decisions - Conclusion reached after Consideration of Knowledge is Considered 15 16 15 16 INFORMATION VALUE CHAIN (EXAMPLE FOR TIDE PODS) IN THE VIDEO: WHAT WERE THE PROBLEMS FOR EACH FIRM? Knowledge –Current and Planned Marketing Campaign and Consumer Response on Tide Pods (what can we learn? So what? 1. Implications?) Decisions –Regarding Future Marketing Campaigns of Tide Pods (what should we do differently in the future for marketing? 2. Should we change the product? Address any major problems?) Watch the video: 4 Google Analyst Real Life Examples 3. 17 17 18 Professor J. Siambanopoulos 4 King's University College Fall 2024 MOS 1033A BUSINESS ANALYTICS Defined as the use of data to create knowledge, to help draw conclusions and address business questions Different business functions have different business analytic needs Marketing needs are different from financial analytics; accounting analytics different from operations analytics What happened? (best/worst, how often, when, how/what method, who is our customer, where are they, etc.) BUSINESS ANALYTICS ACROSS Identifying anomalies and outliers – something different than we expected (here’s something weird that happened) THE DIFFERENT BUSINESS Finding previously unknown linkages, patterns, or relationships FUNCTIONS between variables LO 1.4 21 20 21 DATABASE MARKETING EXAMPLES: WHAT PROBLEMS MARKETING ANALYTICS WERE FACED BY WHICH COMPANIES? Marketing is the “activity, set of institutions, and processes for 1. creating, communicating, delivering, and exchanging offerings that have value for customers” Marketing analytics measures and attempts to improve its performance (4 Ps plans, etc.) 2. Arguably, the most important component of marketing analytics is providing insights into customer preferences and trends This leads deeply into personalization and customization Plus selling that info when it is connected to other data (!!!!!) 3. Watch the video: 5 Database Marketing Examples 22 22 23 Professor J. Siambanopoulos 5 King's University College Fall 2024 MOS 1033A ROLE OF ACCOUNTING BRANCHES OF ACCOUNTING Accounting is a systematic process of measuring, recording, and _____________________ accounting focuses on collecting and analyzing communicating the financial information that decision-makers business performance information for external decision makers need to make decisions. Keeping score of everything _____________________ accounting focuses on collecting and analyzing As the financial language of business, accounting provides business performance information for internal decision makers financial information to decision-makers. ______________ investigates accounting and financial records and processes to help determine if they are in conformity relevant standards or laws ____________ accounting is a branch of accounting which focuses on collecting and analyzing transactions in conformity with tax law 25 26 ACCOUNTING ANALYTICS FINANCIAL ANALYTICS Accounting Analytics uses business analytics to help measure Finance is the management of money by investing, borrowing, accounting performance and address accounting questions in the lending, budgeting, saving and forecasting financial capital audit, financial accounting, managerial accounting and tax areas (money) Analytics (deeper data analysis) can help: Financial Analytics uses business analytics to help a company Evaluate Performance measure and evaluate its financial performance, Mitigate Risk From predicting cash flows from its customers to helping management evaluate future investments based on expected Understand Behaviors investment performance, such returns to investments in equipment Build Business Plans or employee training or stocks and bonds. Organize Business Improvements Find Opportunities Maximize Profits 28 29 28 29 Professor J. Siambanopoulos 6 King's University College Fall 2024 MOS 1033A BRANCHES OF FINANCE OPERATIONS ANALYTICS _____________________________________manages funding sources, capital Operations includes an evaluation of a company’s structure and investment decisions with the goal of increasing the value of the firm for shareholders (owners). (borrowing) Human resource (evaluation of employee efficiency and turnover) IT operations, and Supply chain (e.g., sourcing, distribution and logistics) _______________________________ focuses on acquisition and disposition of assets to help generate profit (or income). (investing) Operations Analytics measure and improve the efficiency and effectiveness of the company’s operations, since operations is all actions needed to run the company and generate income Financial markets and Institutions Getting the “Right Product in the Right Place at the Right Time” Financial markets are the markets for selling various investments including requires extensive data analysis to ensure product fulfilment stocks and bonds, commodities, and derivatives. E.g. TSX, Nasdaq Financial institutions work in financial markets such as banks (e.g., Royal Bank, BMO), investment firms (e.g., pension firms like OMERS, CPP), and brokerages (e.g., Questrade, Wealthsimple) 32 30 32 ROLE OF OPERATIONS AND BRANCHES OPERATIONS ANALYTICS The processes that turn inputs into goods and services that Designed to create data-based, actionable insights to help companies sell companies optimize their decision outcomes. Ensures that an organization’s materials, labor, and other inputs HR analytics (also known as people analytics, workforce analytics, are used in the most effective and efficient way possible and talent analytics) analyzes human resource data to improve a company’s workforce performance. IT operations analytics analyzes company data from various BRANCHES applications, devices, and IT infrastructure to help managers Supply Chain: responsible for the production of a identify, predict, solve, and prevent IT-related issues. product/service and its distribution to the final consumer Supply chain analytics analyzes company data to help managers Human Resources: manages and develops the workforce improve supply chain planning, efficiency, and effectiveness. IT Operations: manages IT hardware, software, and support Watch the video: 6 What Are the Problems Solved By Data Analysts 33 34 Professor J. Siambanopoulos 7 King's University College Fall 2024 MOS 1033A WHAT ARE THE PROBLEMS SOLVED BY DATA ANALYSTS? 1. 2. 3. THE ANALYTICS MINDSET AND THE SOAR ANALYTICS MODEL 4. LO 1.5 35 37 ANALYTICS MINDSET THE SOAR ANALYTICS MODEL (FROM THE TEXT) An analytics mindset is the ability to: 1. Specify the Question Ask the right questions; 2. Obtain the Data Extract, transform and load relevant data; 3. Analyze the Data Apply appropriate data analytic techniques; and 4. Report the Results Interpret and share the results with stakeholders. Source: Ernst & Young Foundation: E&Y Academic Resource Center (EYARC). 2017. The Analytics Mindset. Available online at http://aaahq.org/Education/Webinars/6-7-17-EY-Academic-Resource-Center-An- Overview-of-Analytics-Mindset-Competencies-and-Case-Offerings. NOTE: There are MANY frameworks but they all basically cover the same steps EXHIBIT 1.4 The Recursive SOAR Analytics Model 38 39 38 39 Professor J. Siambanopoulos 8 King's University College Fall 2024 MOS 1033A A BEGINNER’S GUIDE TO THE DATA ANALYSIS PROCESS (FROM THE VIDEO) KEY PERFORMANCE INDICATOR (KPI) 1. Measurable and quantifiable metric used to track progress towards a specific goal or objective 2. These are a good start for any question (since they reflect success/failure in some area of the firm) 3. “Managers pay attention to the things they consider important” 4. If it is important, you will measure it and track it E.g. profit, sales per employee, on-time deliveries, customer satisfaction, 5. sales goals If any of these are “worse than normal”, something may be wrong These are the things you most likely asking about and focusing on Watch the Video: 7 A Beginner’s Guide To the Data Analysis Process 40 40 42 ASK THE RIGHT QUESTIONS ASK THE RIGHT QUESTIONS A good data analytic question is Achievable: should be able to be answered and the answer Specific: needs to be direct and focused to produce a should cause a decision maker to take an action meaningful answer Relevant: should relate to the objectives of the organization or "What is the average revenue per customer?" is more specific the situation under consideration than asking "How is the business doing?” or Timely: must have a defined time horizon for answering "What are your thoughts on the product's features and usability?” is better than "How do you feel about our product?" Measurable: must be amenable to data analysis and thus the inputs to answering the question must be measurable with data "What percentage of customers renewed their subscriptions this year?" is more measurable than asking "Are customers satisfied with the service?" 43 44 43 44 Professor J. Siambanopoulos 9 King's University College Fall 2024 MOS 1033A SOAR: SPECIFY THE QUESTION: SAMPLE BUSINESS SOAR: SPECIFY THE QUESTION QUESTIONS (POTENTIAL ANSWER WITH DATA): Different questions lead to different analytics types How is the customer demographic profile (age, gender, disposable income, etc.) changing for typical customer shopping at Five general types of business questions and their McDonald’s? respective analytics type: If we purchase a new, more efficient copier, will the realized Descriptive Analytics: What Happened? savings be sufficient to justify the more expensive price tag? Diagnostic Analytics: Why did it Happen? How much will the lead ordering deadline for Christmas products Predictive Analytics: What is Likely to Happen in the Future? change if we source the products from Mexico versus Indonesia? Prescriptive Analytics: What Action(s) should we Take, based How will tariffs affect the pricing of products in our stores? on What we Expect Will Happen? Adaptive Analytics: How does the System Adapt to Changes? How will our increasing employee hours affect our level of (not part of our focus in MOS 1033) customer satisfaction with returns/defects/product issues? 45 46 45 46 HOW TO COME UP WITH THE QUESTION: IDEAS HOW TO COME UP WITH THE QUESTION: IDEAS A problem statement should not include any assumptions, Break down the problem into smaller and more manageable opinions, or solutions parts NO close-ended questions (yes/no) Help identify the root causes, the key variables, and the scope of the problem. E.g. Instead of “Do you like our product?” use “What do you like about our product” Use different techniques to break down the problem: It should only focus on the facts and the gap between the current Asking why, what, where, when, and who questions (5 Ws) and the desired situation Who is buying our product? Why? What do they like about it? Etc. Creating a fishbone diagram Write a clear and concise problem statement that describes: Surveys/opinions of the current situation or process (to find issues) What you are trying to achieve If there is a visible problem, look at all angles to figure out what affects the Why it matters, and problem) Who is affected by it 47 48 Professor J. Siambanopoulos 10 King's University College Fall 2024 MOS 1033A FISHBONE DIAGRAM (ROOT CAUSE ANALYSIS) A visual way to look at cause and effect Decide on what problem(s) you want to solve. Start with a clearly defined problem with goals More structured approach than some other tools available for brainstorming causes of a problem (e.g., the Five Whys tool) Understand what stakeholders will be involved What problems do they have? What do they need? The Problem Figure out what data you need (or would love to have) (the effect) What data could provide insights? (this is where business knowledge and data analytics start to mix) Decide how success is measured using KPIs. What gets measured gets managed. Establish key performance indicators with your team that everyone will rally behind. Set up systems that track what you need tracked. E.g. How are Possible Major Causes late shipments, customer complaints, etc. tracked? Accounting department or someone else? 49 50 TYPES OF MARKETING QUESTIONS ANALYTICS CAN TYPES OF MARKETING QUESTIONS ANALYTICS CAN HELP WITH ANSWERING HELP WITH ANSWERING 51 52 Professor J. Siambanopoulos 11 King's University College Fall 2024 MOS 1033A TYPES OF OPERATIONS ANALYTICAL QUESTIONS 53 54 TYPES OF FINANCIAL ANALYTICAL QUESTIONS 55 56 Professor J. Siambanopoulos 12 King's University College Fall 2024 MOS 1033A TYPES OF ACCOUNTING ANALYTICAL QUESTIONS 57 58 SOAR: OBTAIN THE DATA WHERE TO OBTAIN DATA Which data is available? (immediately) First-party data, which is collected directly from users by your Which data needs to be collected? (paid and free) organization Will the data actually adequately address the question? Second-party data, which is data shared by another organization about its customers (or its first-party data) Is the data relevant to the question being asked and/or reliable enough to address the question? Third-party data, which is data that’s been aggregated and rented or sold by organizations that don’t have a connection to Is it clean of errors or inconsistencies? your company or users Does it have lots of missing data? Is the data biased in some way? 59 59 60 Professor J. Siambanopoulos 13 King's University College Fall 2024 MOS 1033A DATA COLLECTION METHODS USED IN BUSINESS EXTRACT, TRANSFORM, AND LOAD RELEVANT DATA ANALYTICS (CREATED INTERNALLY/FIRST PARTY) The process of extracting, transforming, and loading data is often Surveys (internal with employees, external with suppliers, etc.) abbreviated as the ETL process Transactional Tracking (every single sale to a customer) The ETL process is often the most time-consuming part of the Interviews and Focus Groups analytics mindset process Repetitive ETL processes can be automated so the extracting, Online Tracking (clickstream data, web site analytics) transforming, and loading data is done entirely by a computer Observation (Camera footage, customer movement) program in what appears to be a single, unified step Forms (evaluations, post-sale reviews) It isn’t one step but it can look simple (but it isn’t!) Social Media Monitoring Financial reports (budgets, statements, cost/benefit analysis) https://online.hbs.edu/blog/post/data-collection-methods 62 61 62 EXTRACTING DATA TRANSFORMATION Extract or copy raw data from multiple sources and store it in a staging area. A staging area is an intermediate storage area for During the “pull the data from the source” stage you can: temporarily storing extracted data. Refine, sort, organize, clean (if possible), catch big errors like: Data extraction process Put everything into the same format/font/size 1. Locating and identifying the relevant data Separate first and last names (easier to search later and sort) Fix the students that think “Student ID” is their email (jsiamba2 vs. a 2. Perform the data extraction (different places/formats) à number 251232456”) “dump into one spot” (consolidation) Change all blanks (strings) into zeros (or zeros into blanks/strings) 3. Verify the data extraction quality and document what you have Data cleansing, data cleansing, data deduplication, data format revision done We will talk about cleaning data and much more (ETL and related ideas) in next week’s class: Class 8 Obtain the Data 63 63 64 Professor J. Siambanopoulos 14 King's University College Fall 2024 MOS 1033A LOADING EXAMPLE Suppose an organization wants to monitor its reputation Move the transformed data from the staging area into the target data warehouse How effective is our marketing? What are we known for? For most organizations that use ETL, the process is automated, What do customers like/dislike about our products? well defined, continual, and batch driven It may have data from many sources, including online reviews, Loading into your database, data warehouse or ERP software social media mentions, and online transactions (externally) plus (Enterprise Resource Planning) our internal data (customer surveys, product forums, direct More on these types in Class 8 Obtaining the Data feedback on social media) plus all the financial data/results Most of these items are in different formats, levels of completeness, etc. An ETL tool can extract data from these sources and load it into a data warehouse where it can be analyzed and mined for insights into brand perception 66 65 66 APPLY APPROPRIATE DATA ANALYTIC TECHNIQUES SOAR: ANALYZE THE DATA _____________________________________are information that results from the examination of data to understand the past answers to the question “what happened?” _______________________________________build on descriptive analytics and try to answer the question “why did this happen?” ______________________________________are information that results from analyses that focus on predicting the future—they address the question “what might happen in the future?” _______________________________________are Information that results from analyses to provide a recommendation of what should happen—answers the question “what should be done?” More on this topic in Class 9 Analyze the Data 67 68 67 68 Professor J. Siambanopoulos 15 King's University College Fall 2024 MOS 1033A 70 71 70 71 INTERPRETING RESULTS SOAR: REPORT THE RESULTS Interpreting results can be complicated. Data reporting is the process of collecting and presenting data in a structured format to facilitate data-driven decision making One common way people interpret results incorrectly relates to correlation and causation The goal of data reporting is to make data easily understandable _____________________________ tells if two things happen at the same What is the best way to communicate what we’ve found in our data time (but it ONLY means that!) analysis? _______________ tells that the occurrence of one thing will cause Static Visualizations (non-changing) the occurrence of a second thing Reports We will discuss more later Graphs Tables Dynamic Visualizations (changing, usually real-time) Dashboards More on this topic in Class 10 Report the Data 72 74 72 74 Professor J. Siambanopoulos 16 King's University College Fall 2024 MOS 1033A https://www.visual capitalist.com/weal th-distribution-in- america/ 75 76 REPORT THE RESULTS TYPES OF DATA REPORTS ___________________________________is the process of translating often Performance Reports complex data analyses into more easy-to-understand terms and Historical Analysis Reports: Businesses can identify growth relatable concepts to enable better decision making patterns and areas needing improvement by comparing data To tell a successful data story, you will need to over a period Remember the question that initiated the analytics process Industry Benchmarking Reports Consider the audience Visual Data Reports (summaries) Use data visualizations Predictive Analysis Reports Problem Detection Reports 78 77 78 Professor J. Siambanopoulos 17 King's University College Fall 2024 MOS 1033A REPORT THE RESULTS DATA ANALYTICS IS NOT ALWAYS THE RIGHT TOOL _____________________________ is the use of a graphical representation of data to convey meaning Data analytics is not always the correct tool to reach the best outcome. Good principles of visualization design include: Reliable data does not exist for aspects of many questions. Choosing the right type of visualization Human judgment or intuition may be able to account for Simplifying the presentation of data sentiment factors that cannot be reliably measured. Emphasizing what is important Data can help us make better decisions, but we need to remember Representing the data ethically the importance of Intuition, expertise, ethics, and other sources of knowledge that are not easy to quantify but that can have a significant impact Watch the video: 7 How ZARA Uses Data Analytics to Run a on performance. Profitable Business 80 82 80 82 REASONS FIRMS DON’T USE DATA ANALYTICS WHAT IS BUSINESS INTELLIGENCE (VS. ANALYTICS) 1. _______________________________________________________ Business intelligence: Uses past and current data to inform for current issues/problems 2. _______________________________________________________ Identify trends and pattern without the complex statistical analysis The “what” and “how” (descriptive analysis) 3. Analytics and stats can’t help me (I’m too small) Retrospective (like a rearview mirror in a car): where you’ve been and where you are going 4. ________________________________________________________ Business analytics 5. It's a job for the accounting/technology people, not my Use past data to explain current data AND predict what will (or may) department happen in the future Data modeling, algorithms to predict outcomes, E.g. Lana, hairstylist, entrepreneur The “why” and ”what next” (predictive and prescriptive) MAJOR PROBLEM: Forward-thinking (like a map on your phone): where to go next and how to get their efficiently 83 85 Professor J. Siambanopoulos 18