LEARN , STUDY AND THINK WITH SB 🤔🤔🤔: Business Analytics

Chapter 1: Introduction to Business Analytics

Explains the importance of data-driven decision making.
Introduces key analytics types: descriptive, diagnostic, predictive, and prescriptive.
Details how analytics is used in sectors like retail, healthcare, finance, marketing, and manufacturing.
Summarises benefits (informed decision-making, efficiency, competitive advantage, customer understanding, risk management) and challenges (data quality, privacy, skills shortage, costs, resistance to change).
Outlines stages of a business analytics project (problem identification, data collection, analysis, prediction, solution, decision) and ethical issues (privacy, transparency, fairness, security, social impact).

Covers methods for cleaning, integrating, and preparing raw data for analysis.
Focuses on techniques like handling missing values, standardisation, and data transformation.
Explains the use of visualisation tools (Tableau, Power BI, Qlik, Excel) to help stakeholders understand complex insights.
Discusses the role of effective visualisation in communicating results and aiding decision-making.

Introduces the concepts and definitions of probability, random variables, and distributions.
Explains discrete probability distributions (Bernoulli, Binomial, Poisson) and their assumptions.
Describes continuous probability distributions (uniform, exponential, normal), probability density/mass functions, and their applications in business.
Covers outcomes, counting principles, permutations, and combinations, and how probability is used for risk assessment, forecasting, and decision making.

Explains inferential statistics, using samples to draw conclusions about populations.
Discusses hypothesis testing procedures and key terminology (null/alternate hypothesis, significance level, test statistic, p-value).
Covers common tests (z-test, t-test, proportion test).
Discusses types of errors (Type I, Type II) and their implications on business analytics.

Defines data mining and its steps: problem definition, data collection, preprocessing, and analysis.
Explains types of data mining techniques: classification, clustering, association, regression.
Covers both supervised and unsupervised learning, with business applications such as customer segmentation and fraud detection.
Stresses the importance of proper data preparation and ethical use of data in mining projects.

Discusses methods for using historical data to make predictions about future outcomes.
Focuses on modelling techniques such as regression analysis, decision trees, and neural networks.
Covers the practical use of predictive analytics for forecasting, risk management, and identifying growth opportunities.

Explains the theory and application of linear regression models for understanding relationships between variables.
Chapter 7 distinguishes between simple linear regression (one independent variable) and Chapter 8 multiple linear regression (several independent variables).
Covers model assessment, goodness-of-fit metrics, interpretation of coefficients, and application to business problems.

Introduces logistic regression for modelling categorical outcome variables.
Discusses model building, accuracy, sensitivity, and application to classification problems like binary outcomes (yes/no, success/failure).
Emphasises evaluating model performance and its use in real-world prediction tasks.

Provides techniques for making predictions using historical time-dependent data.
Covers qualitative methods (expert judgement, Delphi method) and quantitative techniques (moving averages, exponential smoothing, ARIMA).
Examines business applications (sales forecast, inventory management, energy consumption, market research, climate analysis).
Details the identification of patterns, trends, and seasonal effects in series data.

Explains frameworks for making decisions under certainty, uncertainty, and risk.
Introduces decision criteria (optimistic, conservative, minimax), expected monetary value, payoff tables, and utility theory.
Details normative vs descriptive decision theory and their applications in policy analysis, investment, planning, and risk assessment.

Details the concept and construction of decision trees for classification and regression.
Explains key algorithms: CHAID (Chi-square Automatic Interaction Detection), CART (Classification and Regression Tree).
Discusses metrics (Gini impurity, entropy), ensemble methods (random forest), and strategies for model performance improvements.
Demonstrates practical use of decision trees for visualising and structuring complex decision processes