Fundamentals of Analytics

Fundamentals of Analytics

• Module 1 focuses on analytics in practice.
• Key objectives include understanding analytics concepts, identifying questions analytics can answer, learning analytics practices, and recognizing business users' challenges.
• Further aims involve identifying trends and applications in business analytics, along with applying analytics practices.

What is Analytics?

• Business analytics starts with a dataset or a database.
• Databases require storage solutions, such as computer clouds and data warehousing.
• Database storage necessitates a new term: big data, which involves data sets too large for standard software.
• Little data refers to smaller data that helps businesses track customers.
• Analytics serves in data sorting to find useful information.
• Analytics, Business Analytics, and Business Intelligence are all related terms.
• Analytics is defined as a process using statistical techniques, information system software, and operations research methodologies to explore, visualize, discover, and communicate patterns in data.
• Analytics converts data into useful information applicable across disciplines, illustrated by using weather measurements to predict weather patterns.

Types of Analytics

• Various types exist, necessitating organization for clarity.
• Analytics can be categorized into descriptive, predictive, and prescriptive.
• The Institute of Operations Research and Management Sciences (INFORMS) suggests these groupings.
• Descriptive analytics uses simple statistical techniques to describe what is contained in a data set or database.
• An example of descriptive analytics is creating an age bar chart to depict retail shoppers for targeted ads
• Predictive analytics employs advanced statistical or informational software to identify predictive variables and to build a predictive model.
• An example of predictive analytics is multiple regressions used to show the relationship between age, weight, and exercise on diet food sales.
• Prescriptive analytics uses decision science, management science, and operational techniques to allocate resources.
• An example of prescriptive analytics is when a department store uses programming models to allocate their advertising budget to target customers.
• Analytics types can be independently viewed, for example, providing information for decisions.
• A combination of analytic types helps extract information for planning and decisions.

Purpose of Analytics

• The purposes and methodologies differ among descriptive, predictive, and prescriptive analytics.
• Analytics focuses on insightful information from data, while business analytics uses analytics to improve measurable business aspects.
• The 3 types of analytics are applied in a sequence( descriptive, then predictive, then prescriptive).
• Business analytics (BA) defines as a process beginning with business-related data collection that supports business decision-making.
• Descriptive analytics identifies possible trends in large data sets or databases.
• The purpose of descriptive analytics is to get a rough picture of what generally the data looks like and what criteria might have potential for identifying trends or future business behavior.
• Predictive analytics builds predictive models designed to identify and predict future trends.
• Prescriptive analytics allocates resources optimally to take advantage of predicted trends or future opportunities.
• Descriptive analytics answers what happened and why it happened.
• Predictive analytics answers what will happen.
• Prescriptive analytics anticipates what will happen, when it happened, and also why it happened.
• The three types of analytics are used in business to find explanations with outliers or values out of range on a two-dimensional graph.
• Exploratory data analysis (EDA) is used to visualize data.
• Measures of central tendency, such as means, medians, and modes, express what's going on in data.

EDA

• EDA should be implimented when working with data, for the following reasons:
• To gain intuition about the data
• To make comparisons between distributions
• Sanity checking to make sure the data is on the scale you think it is
• To find out if there is missing data or outliers
• To summarize the data

Analytic Processes

• Data analysis involves collecting data, data repository, analyzing the collected data, and assesses/queries the data.
• Business users can choose required reports like sales, financial, distributions, and inventory.
• To arrive at smart decisions, analytics helps to allow managers to make better and smarter choices when considering the data.

Questions Analytics Can Answer

• Stochastic Optimization: is used to achieve the best outcome by taking into account the effects of variability
• Optimization: is used to achieve the best outcome
• Predictive Modeling: What will happen next if
• Forecasting: What if these trends continue?
• Simulation: What could happen....?
• Alerts: What actions are needed?
• Query/drill down: What exactly is the problem?
• Ad hoc reporting: How many, how often, where?
• Standard Reporting: What happened?

Applications of Analytics

• Analytics has applications in:
• Policing/Security
• Transportation
• Customer Interactions
• City Planning
• Travel
• Fraud and Risk Detection
• Healthcare
• Manage Risk
• Delivery Logistics
• Web Provision
• Proper Spending
• Energy Management
• Internet/Web Search
• Digital Advertisement

Power of Information

• The amount of data available has outstripped the ability to investigate that data.

Metrics and Measurements

• Metrics translate business challenges into operational measures monitored over time, influencing the company.
• Objectives help measure progress and the impact of business analytics.
• Metrics measures include:
• Increase retention and conversion rate
• Increase productivity and market share
• Increase wallet share
• Increase customer satisfaction
• Increase average order size/number of products
• Increase average spend per customer
• Decrease operational costs
• Decrease time-to-decision
• Optimize human capital

When Analytics Isn't Practical

• Analytics may not be practical in the following scenarios:
• When There's No Data
• When There's No Precedent
• When the Decision Maker Has Considerable Experience
• When the Variables Can't Be Measured
• When decisions must be made rapidly without a systematic data gathering, or if it's a first-time scenario
• if a decision-maker has enough experience already, or when key analytical variables cannot be measured.

Challenges of Business Analytics

• Business analytics faces challenges due to the economic environment, competition, and changing customer loyalty.
• The increase in companies relying on business analytics to drive strategy is that customers are becoming more fickle
• Customer loyalty to products and services is rarer than ever before

Secret of Success

• Success in business analytics requires establishing a business analytic culture with understanding analytics in play.
• Analytics allows leaders to recognize the insights needed to gain a competitive advantage.