Instructor: IZANG, A.A (PhD, MSc, MNCS) Lesson One: Introduction to Data Analysis Introduction to Data Analysis Data/Information is the most strategic business asset. It is a collection of facts.
Data analysis is the process of identifying, cleaning, transforming and modelling data (structured or unstructured) in order to get useful insights to support the critical decision- making process.
• Every day we create 2.5 quintillion bytes of data - 90% of the data in the world today has been created in the last two years alone. • This data comes from everywhere: sensors used to gather climate information, posts to social media sites, digital pictures and videos, purchase transaction records, and mobile phone GPS signals to name a few. Such data has been described as the “oil” of the 21st Century digital economy.
• In this context Data Analytics is an important economic driver both nationally
and internationally encompassing the processes of inspecting, cleaning, transforming, and modelling data with the goal of discovering useful information, suggesting conclusions, and supporting decision-making. Introduction to Data Analysis • Data analysis and data analytics. • Two terms for the same concept? Or different, but related, terms?
• It’s a common misconception that data analysis and data analytics are the same thing. However, the generally accepted distinction is: • Data analytics is the broad field of using data and tools to make business decisions. • Data analysis, a subset of data analytics, refers to specific actions.
• To explain this confusion and attempt to clear up this misconception,
a critical look at both terms, examples, and tools will be done here. Data Analytics Vs Data Analysis What is Data Analytics? • Data analytics is a broad term that defines the concept and practice (or, perhaps science and art) of all activities related to data. The primary goal is for data experts, including data scientists, engineers, and analysts, to make it easy for the rest of the business to access and understand these findings.
• Data analytics includes all the steps you take, both human- and machine- enabled, to discover, interpret, visualize, and tell the story of patterns in your data in order to drive business strategy and outcomes. Data analytics can help you: • Find trends • Uncover opportunities • Predict actions, triggers, or events • Make decisions What is Data Analytics? Data analytics is systematic, consisting of many computational and management steps. Experts stress the word “systematic”. Being systematic is vital because data analytics uses many different activities and draws on all types and sizes of data sources. • Many subject areas comprise data analytics, including: • data science, • machine learning, and • applied statistics. • One tangible result of a data analytics practice is likely well-planned reports that use data visualization to tell the story of the most salient points so that the rest of the business who are not data experts can understand, develop, and adapt their strategies. • Think of the many ways data analytics can highlight areas of opportunity for your business: • Using facts, not guesses, to understand how your customers engage might mean you change your sales or marketing processes. A bakery might use its data to realize its demand for bread bowls increases in the winter—which means you don’t need to discount the prices when demand is high. • An increase in cyberattacks might mean you need to take proactive preventative measures. • Data from a variety of IoT devices in a certain environment, such as your server room, a power station, or a warehouse, could indicate whether you are providing the safety and reliability you need at the lowest cost possible. Processes in data analytics The data analytics practice encompasses many separate processes, which can comprise a data pipeline: • Collecting and ingesting the data • Categorizing the data into structured/unstructured forms, which might also define next actions • Managing the data, usually in databases, data lakes, and/or data warehouses • Storing the data in hot, warm, or cold storage • Performing ETL (extract, transform, load) • Analyzing the data to extract patterns, trends, and insights • Sharing the data to business users or consumers, often in a dashboard or via specific storage Processes in data analytics What is data analysis? • Data analysis consists of cleaning, transforming, modeling, and questioning data to find useful information. Consider data analysis one slice of the data analytics pie. (It is generally agreed that other slices are other activities, from collection to storage to visualization.)
• The act of data analysis is usually limited to a single, already prepared dataset. You will inspect, arrange, and question the data. Today, in the 2020s, a software or “machine” usually does a first round of analysis, often directly in one of your databases or tools. But this is augmented by a human who investigates and interrogates the data with more context.
• When done with analyzing a dataset, other data analytics activities are used to: • Give others access to the data • Present the data (ideally with data visualization or storytelling) • Suggest actions to take based on the data
• A vital point of data analysis is that the analysis already captures data, meaning data from the past. Type of data analysis There are many types of data analysis techniques. Here are the most well- known: • Text analysis. This is also referred to as Data Mining. This method discovers a pattern in large form data sets using databases or other data mining tools.
• Statistical analysis. This analysis answers “What happened?” by utilizing past data in dashboard form. Statistic analysis involves the collection, analysis, interpretation, presentation, and modeling of data.
• Diagnostic analysis. This analysis answers “Why did it happen?” by seeking the cause from the insights discovered during statistical analysis. This type of analysis is beneficial for identifying behavior patterns of data. Type of data analysis • Predictive analysis. This analysis suggests what is likely to happen by utilizing previous data. The predictive analysis makes predictions about future outcomes based on the data.
• Prescriptive analysis. This type of analysis combines the insights from text, statistical, diagnostic, and predictive analysis to determine the action(s) to take in order to solve a current problem or influence a decision.
• Cognitive analysis: Cognitive Analytics applies human-like intelligence to
certain tasks, and brings together a number of intelligent technologies, including semantics, artificial intelligence algorithms, deep learning and machine learning. Type of data analysis • Data Analytics has evolved over the years from • Descriptive (what has happened) to • Diagnostic (why did it happen) to • Predictive (what could happen) to • Prescriptive (what action could be taken).
• The next big paradigm shift will be towards Cognitive Analytics which will exploit the massive advances in High Performance Computing by combining advanced Artificial Intelligence and Machine Learning techniques with data analytics approaches. Data Analysis Approaches
Figure 3: Data Analytics Approaches
Which is better? Consider the differences between: • An analyst sending a business user a spreadsheet of numbers versus creating a dashboard for the user to interact with descriptive analytics.
• A business user receiving a report with the live value of a marketing
campaign versus creating a web app that both shows the forecast and lets the user interact with predictive analytics.
• The ultimate move, is creating a product that makes a data-driven
prediction and contacts another system’s API is order to produce action. This is data analytics in action. Tools for data analytics • Analytics software are tools that help humans and machines perform the analysis that allows us to make mission-critical business decisions. • Common tools for performing data analysis and overall analytics include: • Microsoft Excel • Microsoft Power BI • Tableau • R analytics • Python • Google Analytics Why the confusion? Interestingly, the terms are sometimes confused by data scientists and data analysts themselves! • Polling a variety of people in the wide world of data revealed this divide. Most agreed that data analytics is the broader field, of which data analysis is one key function, but others had different takes. • This lack of clarity underscores that maybe the question isn’t data analytics versus data analysis—but whether you’re doing both as well as you can.
• Several people said that they aren’t concerned if us non-data experts use the terms interchangeably.
