IT3080 Data Science & Analytics Lecture 01 PDF

Summary

This lecture introduces data science and analytics, highlighting the importance of data-driven decision-making in business. It covers data types, analysis techniques, and how these techniques can be used to create business values. The lecture also discusses various levels of intelligence and how organizations can use data for various outcomes.

Full Transcript

INTRODUCTION TO DATA SCIENCE & ANALYTICS DATA SCIENCE & ANALYTICS (IT3080) OVERVIEW Data-driven decision making Introduction to data science and analytics Management and processing of data Techniques to derive business values from data LEARNING OUTCOMES Identify the benefits of data-driven d...

INTRODUCTION TO DATA SCIENCE & ANALYTICS DATA SCIENCE & ANALYTICS (IT3080) OVERVIEW Data-driven decision making Introduction to data science and analytics Management and processing of data Techniques to derive business values from data LEARNING OUTCOMES Identify the benefits of data-driven decision making Explain different techniques used to derive business values from data Identify different data types and represent them using appropriate methods Compare and contrast different data analytics techniques HOW MUCH DATA DO WE CREATE DAILY?  Businesses and users produce massive amount of data every day.  90% of the data on the internet has been created since 2016!  Facebook users also click the like button on more than 4 million posts every minute!  Instagram users post 46,740 pictures every minute.  656 million tweets are posted per day! ARE THESE DATA USEFUL?  Understanding data created by users is useful for business organizations in many ways.  For example, Business organizations could  Identify current and potential audience  Identify emerging trends  Identity how audiences are interacting with your content and  Understand what active customers think and feel about your brand  These information are useful for organizations improve their business potentials, improve customer base and improve their marketing strategies. DATA-DRIVEN DECISION MAKING  Despite the availability of data, decision making in an business organization mostly occur based on instincts or gut feeling.  As humans, however, it is possible that we make mistakes because we cannot oversee everything that is happening within our business.  Data driven decision making is helpful to make business decisions backed up by analyzed data. WHAT DECISIONS CAN BE MADE USING DATA?  Strategic decision making : Strategic decisions consider the entire organization and represent a complex aspect of business planning.  What is the trend?  What plans should we make?  Operational decision making : Operational decisions relate to the daily operations of an organization.  What’s happening right now?  What action needs to be taken? DATA SCIENCE AND ANALYTICS  Data science is a multidisciplinary field that deals with technologies, processes, and systems to extract knowledge and insight from data and supports reasoning and decision making under various sources of uncertainty.  There are two aspects of data science that are of interest:  the management and processing of data  the analytical methods and theories for data analysis and optimization DATA SCIENCE AND ANALYTICS (CONTD.)  The first aspect involves data systems such as databases and warehousing and their preparation, including, data cleaning and engineering, and data monitoring, reporting, and visualization.  The second aspect involves data analytics and includes data mining, text analytics, machine and statistical learning, mathematical optimization, and visualization. AN OVERVIEW OF DATA SCIENCE AND ANALYTICS MANAGEMENT AND PROCESSING OF DATA  The foundation of data analytics is having appropriate data that are of sufficient quality, appropriately organized for the analysis task at hand.  Unfortunately, data seldom arrive in a suitable state, and a necessary first step is getting them into a proper form to support analysis.  Thus, prior to data analytics data should be specially prepared for the task of analytics. MANAGEMENT AND PROCESSING OF DATA(CONTD.) Some common data processing tasks are as follows :  Data assessment and cleaning  Data integration  Data transformation DIFFERENT TECHNIQUES OF DATA ANALYSIS Reports (Standard & Forecasting Ad-hoc) Predictive analysis Online Analytical Optimization Processing (OLAP) Alerts Statistical Analysis LEVELS OF INTELLIGENCE CREATING BUSINESS VALUES STANDARD REPORTS  Generated on a regular basis and describe just "what happened" in a particular area.  Example:  Monthly or quarterly financial reports.  Monthly sales reports  They're useful to some extent, but not for making long-term decisions. AD HOC REPORTS  Ad Hoc Reports are customized reports which are useful to obtain data required by business users  Business users can generate their own reports by modifying the Standard report queries or filter values and get the real time data on demand.  Example:  Report that show how many items were sold over a certain period  Custom reports that describe the number of hospital patients for every diagnosis code for each day of the week. QUERY DRILLDOWN (OR OLAP)  Online analytical processing (OLAP) is a technology that could perform multidimensional analysis at high speeds on large volumes of data.  Users are able to analyze multidimensional data interactively from multiple perspectives.  The most important mechanism in OLAP which allows it to achieve such performance is the use of aggregations  Example:  Find the number of laptops sold in Q1 in Australia  Find the revenue from selling TVs from all continents in Q2 ALERTS  An alert is an automated message or notification sent via email,& etc, which indicates that a predefined event or error condition has occurred and that some action is needed.  Alerts allow users to receive critical business information in the quickest and most efficient possible way.  For example, a store manager can be automatically informed when in-stock levels of a critical STATISTICAL ANALYSIS  Statistics are techniques of analyzing and interpreting numerical data for making inferences about the population, from the picked out sample data.  They can be used by business experts to solve their problems.  Example techniques:  Descriptive statistics : Identify mean, median, mode of sales in a month  Inferential statistics : Compare differences between two groups of buyers  Causal analysis : Identify factors effecting a person to go for digital banking FORECASTING  It’s a projection of a business’s future developments based on trends, patterns, and current and historical data analysis  Business forecasting allows your company to make long term plans and prepare for any changes in the market  Example:  Time series: Forecasting sales revenue in future PREDICTIVE MODELLING  Predictive analysis is implemented to make a prediction of future events, or what is likely to take place next, based on current and past facts and figures.  Example techniques:  Association Rule Mining  Classification  Regression  Neural Networks OPTIMIZATION Optimization is widely used in business analysis for identifying the best possible action for a situation.  While other statistical analysis might be deployed for driving exclusions, it provides the actual answer. Basically, it focuses on discovering the optimal suggestion for a process of decision making. THANK YOU

Use Quizgecko on...
Browser
Browser