EXPLORE / TEST / EXPLAIN

Applied Analytics Lab.

Change the example. Inspect the output. Five public demonstrations turn survey, licensing, feedback and data-engineering ideas into working lessons.

Some assignments later informed my workplace practice using closely aligned synthetic data and, where appropriate, organisational datasets. These public tools are newly built teaching versions with fictional data—not a release of those datasets, recovered models or institutional performance claims.

Loading the five analytics tools…

Personal tool suggestions

Enable JavaScript to choose optional feedback-based suggestions.

EXPLAINABLE AI & DATA / READ THE METHOD

Different questions need different methods.

The Applied Analytics experiments distinguish numerical prediction, text themes, survey summaries and data cleaning. Their demonstration data does not establish real-world effectiveness.

Follow the reasoning.

InputChoose an authored scenario
PrepareApply the selected data or text transformation
AnalyseRun the exported or deterministic method
InspectRead the errors, signals and exclusions

Explore the building blocks.

AI Capability3

AI/Data Concepts1

Algorithm3

Data Science Pipeline1

Evaluation & XAI1

Python Package2

Responsible AI1

Number of concepts in this guide, not performance or usage measures.

Explore the explanation matrix · 12 concepts

Concept categoryFind a term or example

12 concepts shown

On small screens, scroll the table sideways. “Learning context” explains a related idea; it does not mean that method runs on this page. Deep learning is the standard term for “deep ML”.

Technical term	Technical description / definition	In plain English	How this page uses it
Ridge regressionAlgorithm	A linear regression model with an L2 coefficient penalty to limit excessive parameter magnitude.Primary reference ↗	Fit a trend while discouraging overly extreme weights.	Running here The numerical predictor computes an intercept plus weighted inputs from the exported Ridge model.
Random forestAlgorithm	An ensemble of decision trees whose outputs are combined for classification or regression.Primary reference ↗	Several branching rulebooks contribute to one estimate.	Running here The classifier averages outputs from exported decision trees.
Multinomial Naive BayesAlgorithm	A probabilistic classifier using feature counts and class-conditional independence assumptions.Primary reference ↗	Count familiar words and compare which labelled themes they tend to accompany.	Running here The text experiment tokenises words and uses the exported multinomial Naive Bayes probabilities for themes.
Natural language processing (NLP)AI Capability	Computational methods for representing, analysing or generating human language.Primary reference ↗	Help a computer work with words, while remembering that context matters.	Running here This theme classifier works with word counts and a fixed vocabulary; it is not a conversational language model.
Sentiment analysisAI Capability	A language-analysis task that estimates an expressed attitude, often as polarity or sentiment categories.Primary reference ↗	Estimate the tone of words—not the private feelings or personality of their author.	Learning context A topic such as support or communication is not itself a positive or negative sentiment label.
Data quality checksData Science Pipeline	Validation of completeness, allowed values, uniqueness, types and consistency with expected constraints.Primary reference ↗	Check missing, repeated and impossible entries before trusting a chart.	Running here Cleaning experiments identify duplicated IDs, missing entries and out-of-range survey values; policy can stop or exclude them.
Descriptive analyticsAI/Data Concepts	Summaries of observed data using counts, rates, distributions or comparisons.Primary reference ↗	Tell us what the records show; this alone does not predict next week.	Running here Survey views calculate means and positive-response counts for available values in the selected cohort.
Held-out evaluationEvaluation & XAI	Assessment on examples excluded from fitting and model selection, according to the declared split.Primary reference ↗	Keep some answers out of practice so the test means something.	Published analysis Exported test evidence is limited to the authored synthetic training and evaluation design.
NumPyPython Package	A Python library for multidimensional arrays and numerical operations.Primary reference ↗	The numerical toolbox behind many Python calculations.	Build-time Python NumPy supports training data and model preparation.
scikit-learnPython Package	A Python library providing estimators, preprocessing tools and model-evaluation utilities.Primary reference ↗	A toolkit of models and fairer ways to test them.	Build-time Python Ridge, RandomForestClassifier, CountVectorizer and MultinomialNB are used in the training scripts.
Coverage, bias and representationResponsible AI	Assess how sampling, labels, missing groups and design choices affect error and applicability.Primary reference ↗	Ask whose experience the data includes—and whose it misses.	Responsible use Unknown vocabulary and ambiguous scores limit applicability; no personal judgement is inferred.
Deep learningAI Capability	Machine learning using neural networks with multiple representation-learning layers.Primary reference ↗	A layered model learns useful representations; more layers do not guarantee a better answer.	Learning context The lab’s exported models are not a deep neural network.