ACG3341 Chapter 13 (Cost Accounting & Control 1) (6th chapter we did; after Chapter 5)

Big Data is structured or unstructured data generated from a variety of sources in volumes too large for traditional technologies to manage in a timely manner.

1. Structured Data (Means exactly what you think it means)
2. Unstructured Data (Means exactly what you think it means)

Hard Data: Verifiable and backed up by reliable sources

Soft Data: Based on qualitivtive inputs like ratings or surveys

Data: consists on unstructured figures and facts

Information: is proccessed & strcutured data that is capable of being useful

CRM (Customer relationship management) use to track and manage past, present and potential customers

ERP (Enterpirse Resource Planning) is when all the software a company uses is combined into one single, massive, all-in-one system

Data Identifier : A unique label for a specific piece of data

Cleaning Data: The process or fixing data

Step 1: Replace obvious errors
Step 2: Removing duplicate entries (Middle Ground)
Step 3: Requires deep study to fix these errors

1) Descriptive Analysis: Describes what already happened or what is currently happening
*What Happened?

2) Diagnostic Analysis: Attempts to make sense of the observations / patterns detected.

*Why did it Happen?

3) Predictive Analysis: Uses observations & patterns to try and predict the future

*What will Happen?

4) Prescriptive Analysis: Used to tell you what to do to reach a desired outcome

*What should we do?

Numerate: Having the ability to understand and work confidently with financial & numerical data

According to the text book:
-The associaition rule = a data-mining technique that looks for cause-and-effect relationships in data.

BUT, according to google, it only looks for correlations in data (and correlation does NOT equal causation)

1. Descriptive Analysis
-Data Visualization: Which just presents data visually

2. Diagnostic Analysis
-Drill Down Techniques & Data Slicing (these are basically to slice / break down data to specific sub categories - product, region, store - to better understand the data )(PS: I don't understand this, they barley explained it in the textbook)

3. Predictive Analysis
-Association Rules
-Regression Analysis

4. Perscriptive Analysis
-Machine learning Tools (To test all possible scenarios and rank them by their probability of occurrence)
-Simulations
-"What if" or Sensitivty Analysis

1. Use your business and accounting skills to understand the business that you work for.
("To be a team player and problem-solver, you must understand your company’s mission, vision, values, customers, vendors, position in the industry, and competitors, as well as what shapes the industry overall. It’s hard to provide insights and move your teams and projects forward if there are gaps in your understanding of what your company does.")

2. Be curious and hone your critical-thinking skills.
("Curious people naturally ask why and how, peeling back the layers to learn how things work. If we take our cues from data scientists, we make new discoveries by “swimming in data.” Look for patterns and new applications of your learning. Dive deeper to find the causes of problems to resolve them in the long term. You can then apply your understanding to business situations and make a splash at work.")

3. Be an effective communicator.
("Related to data analytics, your communication skills can make a big impact in two ways: (1) tell the story of data and (2) act as an interpreter. As a numerate accountant or business student, with foundational data analytics skills, you’ll be able to effectively combine your understanding of the business with output from data scientists, find the meaning, and deliver the most important points to decision-makers.")

4. Get comfortable with ambiguity and/or failure.
("Accepting ambiguity and failure means having “grit”—being determined and tenacious enough to keep going when conditions are difficult and solutions aren’t obvious. Leading and making decisions is hard work. If you don’t already have grit, develop it")

5. Develop technical/data analytics skills.
("Develop a baseline proficiency in at least one option in each of the following four areas: (1) statistics (regression, correlation, and statistical significance), (2) basic data manipulation (Excel proficiency with pivot tables, V-lookup, charting, and sorting), (3) data analytics and visualization software (Tableau, Power BI, Python, R, SAS, and Alteryx), and (4) database management (Access and SQL).")