Business analytics

Producing an analysis has become cheap, but judging one has not. This resource prepares managers for the part of analytics that remains theirs: framing consequential business questions, directing AI-assisted analysis, and deciding whether a result deserves action. Students use AI to generate Python code but learn enough to read it, test it, and spot problems like data leakage and misleading charts. Organized around CRISP-DM, the resource moves from data exploration and cleaning through regression and classification to deployment, strategy, and responsible analytics, ending in a capstone project. Students leave able to brief an analyst or AI assistant, explain what was tested, and defend a decision to a skeptical executive audience.

A statistically polished answer is not yet a defensible decision. This resource teaches business students to tell the difference. Using the CARE framework, students learn to ask whether data is credible, the analysis appropriate, the interpretation responsible, and the action ethical and effective, then report findings in a decision-focused business write-up. The resource builds from descriptive statistics, probability, and inference through ANOVA, regression, forecasting, clustering, and machine learning, including decision trees, neural networks, and large language models. Students run analyses in both R and Python, finishing able to interpret data, challenge weak conclusions, and drive results in any organization.

AI can produce a forecast in seconds, but only analysts who understand the logic underneath can tell whether to trust it. This resource builds that understanding in Excel, where students see the inner workings of core models instead of treating them as black boxes. With business understanding at its core, students learn the four types of analytics, then work through business intelligence, data warehousing, statistical modeling, forecasting, optimization, simulation, data mining, and natural language processing, applied across marketing, finance, and operations. Throughout, AI enhances and externally validates their solutions, and the resource closes with AI tools and ethics, preparing students to use AI with both confidence and judgment.

Spreadsheets show the numbers, but Power BI shows what they mean. This module helps students move beyond spreadsheets into interactive reporting and dynamic decision support, using real-world financial and accounting data. Following the typical Power BI workflow, students connect to and shape raw data with Power Query, build relational models, create calculated fields and measures with DAX, and design reports with effective charts and dashboards. Guided follow-along videos, practice datasets, and check-your-work files support each step, and a final FP&A performance and profitability project brings it all together. Students leave able to tell powerful business stories in budgeting, forecasting, auditing, and performance analysis.

Predicting what will happen is only half the job. Prescriptive analytics tells decision makers what to do about it. This resource, which builds on introductory Python and statistics, takes students from retrieving and analyzing data through forecasting, simulation, classification, clustering, and text analytics, then into the optimization models at the heart of prescriptive work: linear programming, distribution and network models, and decision making under uncertainty. Students build their models in both Excel and Python, applying them to real problems in supply chain, finance, marketing, healthcare, and more. They finish with a final project, ready to recommend the best action and minimize risk.

This resource introduces students to data mining using the CRISP-DM methodology. It is intended for students and business professionals who are interested in using information systems and technologies to solve organizational problems by mining data, but who may not have a background in computer science. Students will learn the concepts and techniques required to successfully mine data in AI Studio, R, and Python.

Structural equation modeling is a procedural skill, and it is best learned by watching it done. This resource takes students from zero knowledge to confidently testing their own theories, showing them how to run each analysis, what the results mean, and why they come out the way they do. Built around visual, step-by-step instruction that shows where to click and what to type, it covers fundamental statistical concepts, hypothesis testing, statistical assumptions, exploratory and confirmatory factor analysis, and structural modeling. Students apply it all in a final project, then earn a certificate of completion. With a focus on concepts and procedures rather than underlying algorithms, it prepares students to conduct analyses independently and confidently.

Building a model is only part of machine learning. The real challenge is getting it into production and keeping it reliable. This resource takes students through the full journey in Python, from data collection and preparation with pandas and APIs to multiple linear regression, decision trees, classification, ensemble methods, model evaluation, and feature selection. Students learn the two purposes of modeling, causal explanation and prediction, and then deploy, monitor, and manage their own machine learning pipelines. A final project and technical interview preparation round out the experience, along with modern AI-assisted workflows, so students are ready to build, evaluate, and manage models responsibly in real organizations.

Which test fits the question? Business decisions often depend on answering that correctly, and this resource teaches students to do it using R. Students begin with the statistical decision-making process, sampling, types of variables, and descriptive statistics, then move through probability, t-tests, and the full family of ANOVA methods (one-way, two-way, repeated measures, and mixed factorial). From there they tackle correlation, simple and multiple regression, chi-square tests, logistic regression, and nonparametric methods. Students learn to describe current business data, make estimates about larger groups, and predict future conditions, building the skills to inform smart business decisions.

Every organization collects data, but the people who can turn it into decisions are in demand, with the U.S. Bureau of Labor Statistics projecting 34 percent growth in data science jobs through 2034. This resource teaches students with little or no programming or statistics background to be those people, using Python. Students progress from programming fundamentals through cleaning, profiling, and visualizing real datasets, into applied statistics like correlation, regression, and group comparisons. They finish with data storytelling and a capstone project that produces a full analysis supporting a real business decision. An automated Python grader gives immediate feedback on coding exercises, and students learn to work alongside AI tools throughout.

Choosing the right machine learning algorithm matters as much as running it, and this resource teaches students how to choose. Rather than treating algorithms as black boxes, students examine how each one works so they can see its strengths and weaknesses and know which problems it suits best. They build hands-on experience with the major techniques, including decision trees, multiple and logistic regression, time series forecasting, k-nearest neighbors, neural networks, gradient boosting, random forests, cluster analysis, and support vector machines, while learning to avoid overfitting and detect anomalies. Students work across Python, Jupyter Notebook, Google Colab, SAS JMP, Excel, and Azure Machine Learning Studio, then bring it all together in a capstone project. They leave with the knowledge to apply machine learning to real organizational problems.

Students can build machine learning models without writing a line of code. Using Tableau, Excel, and Azure Machine Learning Studio, this resource walks students through the CRISP-DM methodology, from visualization and exploratory analysis to complete machine learning pipelines covering data cleaning, algorithm selection, feature selection, and model optimization. They also apply natural language processing and recommendation engines, then finish with a capstone project that brings it all together, building practical skills with industry-standard software.

Anyone can generate a chart or a model with AI in minutes. The harder question is whether the result is strong enough to guide action. This resource teaches students to answer it, building data literacy and model awareness through Python and AI-assisted workflows. Following one process from business question to recommendation, students learn Python fundamentals, then use the CRISP-DM framework to clean data, engineer features, and build and evaluate regression and classification models. They also learn to communicate results, govern analytics responsibly, and check bias and ethics. An end-to-end pipeline project and technical interview preparation give students a portfolio-ready finish.