22576 Fundamentals of Business Data Analytics

How 22576 is assessed

The four weights come from the assessment overview in the Week 1 workshop and match the weighting shown on each assignment page. The Week 1 slide gives 9 September for the group report, while the assignment page and the brief give Monday 14 September 2026; the assignment page is the current one. Late reports lose 5% per day for up to seven days and are not marked after that; late presentation slides lose 20%.

Current 22576 dates

Dates are as published in the Spring 2026 assignment pages, the Quiz 1 page and the quiz schedule on the Assessment 1 page. Confirm exact deadlines and submission settings in the live LMS.

What 22576 covers

The subject runs in two halves. Weeks 1 to 5 wrangle and describe data: data types, keys and joins, quality checks, summary statistics, anomalies, enrichment, clustering and hypothesis tests. Weeks 6 to 11 predict: linear regression and its extensions, model evaluation, and logistic regression with the confusion matrix.

It approaches analytics as accountants and managers use it, and no coding is needed. The tools are Excel, Power Query and KNIME, a code-free platform in which a workflow is built by connecting nodes.

The Spring 2026 offering runs as a weekly one-hour workshop for concepts and a two-hour lab tutorial for hands-on skills, with readings and videos before class and revision activities after it.

The first half of the subject is about getting data ready and describing it: data types and structures, the CRISP-DM process, keys and joins, the five dimensions of data quality, treatments for missing values, summary statistics, outliers, normalisation, enrichment and the unit of analysis, cluster analysis, sampling, confidence intervals and t-tests.

The second half is about prediction: linear regression with dummy variables and controls, log, standardised, time-series and interaction models, holdout testing and the regression assumptions, and logistic regression evaluated with a confusion matrix.

There is no final exam.

Four in-class quizzes, sat on lab computers in Weeks 4, 6, 10 and 12, test both concepts and applied work in Excel and KNIME, and the average of the best three counts. A group of four analyses lead data for an online education company, writing an exploratory report and then presenting it at a round table where each member answers questions on their own analytical role.

Finally, each student builds and compares predictive models on the same data and writes a business report with recommendations.

This guide follows the teaching weeks. Every chapter works an example with its own numbers, draws the key relationship as a figure and ends with quiz-style practice, and the closing chapter turns the rubrics into submission checklists.

Worked example · free

Read a regression of monthly sales on advertising spend

Key terms

Business analytics

The disciplined use of data to reach better business decisions, covering descriptive, predictive and prescriptive work.

Data wrangling

Cleaning, transforming and managing raw data so it is reliable and easy to analyse, through discovery, structuring, cleaning, enriching, validating and publishing.

Data dictionary

A document that records each dataset's variables, what they mean, their types and their source systems, used to plan cleaning and analysis.

Composite key

An identifier built by combining two or more columns when no single column uniquely identifies a row.

Winsorisation

An outlier treatment that replaces extreme values with the nearest acceptable value instead of deleting the observations.

Interquartile range

The spread of the middle half of sorted data, Q3 minus Q1, which sets the box-plot fences at 1.5 times the IQR.

Unit of analysis

The level at which a question is answered and the thing each row represents, such as a customer, a store or a firm.

Silhouette value

A clustering quality measure from −1 to 1 that combines cohesion and separation; higher values mean a better match to the cluster.

Standard error

The expected variation of a sample mean from sample to sample, the standard deviation divided by the square root of the sample size.

P-value

A probability from a test statistic, compared with thresholds such as 0.05 to decide whether to reject the null hypothesis.

Reference group

The category left out when dummy variables enter a regression; the intercept describes it and each dummy is measured against it.

Holdout set

Data kept out of model training and used afterwards to test predictions on observations the model has never seen.

Confusion matrix

A cross-tabulation of actual against predicted classes that counts true and false positives and negatives.

22576 FAQ

Questions students ask in each 22576 chapter

What is the difference between descriptive and predictive analytics?

Descriptive analytics summarises past performance and looks for root causes, answering what happened and why. Predictive analytics forecasts what will happen. In this subject the descriptive weeks come first, covering wrangling, summary statistics, clustering and tests, and the predictive weeks follow with regression and classification models built in KNIME. Chapter 01 · Business Analytics, Data Types and Data Structures

When should I append rather than merge?

Append when the tables have the same columns but different rows, such as January and February sales in the same layout; the rows are stacked. Merge when the tables hold different columns about the same entities, such as customer details and order values, joined on a shared key. Chapter 02 · Data Discovery, Structuring and Joining Datasets

When should I delete rows with missing values?

When only a few values are missing, roughly under 10 to 20% of a column, and the sample is large enough to lose them. Deleting is a poor choice when the sample is already small, because every lost row weakens later tests and models, and imputation may serve better. Chapter 03 · Data Quality Assessment and Cleaning

When is the median better than the mean?

When the data are skewed or contain outliers. A few very large values pull the mean towards them, so it can sit above most observations, while the median stays with the typical case. Summary tables report both, and a large gap between them is itself a sign of skew. Chapter 04 · Descriptive Statistics, Anomalies and Normalisation

What is the unit of analysis?

It is the level at which a question is answered and what each row of the data represents, such as a customer, a transaction, a store or the whole firm. The same question about satisfaction can be asked at each level, and each gives different patterns and conclusions. Chapter 05 · Data Enrichment and Units of Analysis

When should I use k-means rather than hierarchical clustering?

The workshop links k-means to larger samples, over about 500 observations, and hierarchical clustering to smaller ones. k-means needs the number of clusters fixed in advance, whereas a dendrogram lets you choose it afterwards by deciding where to cut the tree. Chapter 06 · Cluster Analysis with k-Means and Hierarchical Methods

Does a larger sample fix a biased sample?

No. A larger sample reduces sampling error, the natural variation from using a sample, but if some customers are more likely to be selected, such as only unhappy customers answering a survey, the bias remains however many replies arrive. Random selection is the remedy for bias. Chapter 07 · Sampling, Standard Error and Confidence Intervals

How do I decide whether to reject the null hypothesis?

Compare the p-value with the threshold chosen in advance, usually 0.05, or 0.01 and 0.1 as alternatives. If the p-value is below the threshold, reject the null and support the alternative; otherwise report that the evidence is insufficient, rather than claiming the null has been proved. Chapter 08 · Hypothesis Development and t-Tests

Why must one category be left out of a dummy regression?

The excluded category is the reference group that the others are measured against; the intercept describes it and each dummy coefficient is a difference from it. If you let KNIME choose, it picks the reference itself, so the tutorial builds dummies explicitly and leaves out the chosen baseline. Chapter 09 · Linear Regression: Building and Interpreting Models

How do I interpret a log-log coefficient?

As an approximate percentage effect: a 1% rise in X goes with about a coefficient-sized percentage change in Y. For larger changes use the conversion S = [(1 + %ΔX)^b1 − 1] × 100, which with b1 = 0.8 and a 10% rise gives 7.92% rather than 8%. Chapter 10 · Advanced Regression and Model Evaluation

How do I interpret a logistic coefficient for a 0/1 variable?

Convert it into a percentage change in the odds with (e^b − 1) × 100%. A coefficient of 1.20 gives about 232%, so the odds of the event are about 232% higher when the variable equals 1 than when it equals 0, holding other variables constant. Chapter 11 · Logistic Regression and the Confusion Matrix

How to prepare for the assessments

Work the subject in the order it is taught and keep the tools open while you study. For each week, read the pre-class sections, then redo the tutorial in Excel or KNIME from a blank workbook or canvas until you can do it without the guide, because the applied quiz questions ask you to produce numbers from a fresh dataset.

Keep a one-page rule sheet as you go: the five quality dimensions, the missing-value thresholds, the 1.5 × IQR fence, the z-score, the standard error and the 90, 95 and 99% multipliers, the test-choice rules, and how to read a coefficient, a dummy and an odds conversion. Before each quiz, redo the worked examples for its weeks under a timer.

For the group report, write each decision down when you make it, with its reason, so the documentation the rubric rewards already exists. For the individual report, choose models that suit the outcome variable, compare them on the same holdout data and finish with recommendations a manager could act on.

Your AI Business Analytics tutor for 22576

Stuck on a hard 22576 question? Sia is AskSia’s AI Business Analytics tutor — ask any 22576 Fundamentals of Business Data Analytics question and get a clear, step-by-step explanation grounded in how the course is actually taught and assessed. Read this whole study guide free, then take your hardest questions to Sia.