AI & DATA SCIENCE / OPERATIONS

Procurement intelligence

A workplace question informed the design; synthetic records were used to test the models.

How the use case emerged

Observation and stakeholder conversations pointed to delays and uncertainty in a procurement workflow. I translated the problem into a set of decision-support questions: where might a request stall, what needs review and which parts of the process could be improved?

REAL-WORLD INPUTProcess discovery and stakeholder needsMODEL INPUTCurated synthetic transaction records

A February 2026 retrospective deck records 26 validated process pain points gathered across stakeholder groups and describes how earlier analysis supported a later funding decision. That refers to the separate process-automation work, not a result delivered by these synthetic models. The predictive-control presentation dated 30 January 2026 narrowed the exploratory model ideas to four explainable questions. Internal documents and individuals remain unpublished.

Why synthetic data

The model exercise did not use live financial or person-level purchase order records. I constructed a 5,000-record synthetic purchase-order dataset with illustrative timing, workflow, spend and emissions fields. It allowed preparation, prediction and anomaly methods to be tested without exposing workplace transactions. Results on those examples are demonstrations, not measured operational outcomes.

The four investigations

01 / REQUESTPurchase-order delay

Could an early risk signal help a reviewer prioritise requests likely to wait?

02 / APPROVALStage-level delay

Which part of a multi-stage approval might need attention, with workload and rules in context?

03 / EXCEPTIONUnusual patterns

Could an explained anomaly flag focus human review without treating a flag as evidence of wrongdoing?

04 / SUSTAINABILITYCarbon estimate

Could a provisional estimate make an environmental trade-off visible, with uncertainty stated?

View the synthetic model charts and their limitations ↗

Feature-importance bars from a synthetic purchase-order delay model, led by requisitioner experience and supplier lead time — **Actual notebook output / fictional records**Relative feature importance in one synthetic delay model. It explains the model's reliance on inputs, not why a real request stalled.

Synthetic confusion matrix with 1 non-delay correctly identified, 34 false delay flags, 12 missed delays and 153 detected delays — **A limitation worth seeing**One synthetic test flagged 34 of 35 non-delayed cases. That false-alarm rate calls for better baselines and validation before any real-world pilot.

The analytical work

A Python notebook cleaned illustrative records, checked missing and implausible values, created timing and workflow features, then compared task-specific models and explanations. It also considered simpler rules and process redesign as alternatives. The point was to make an early review signal testable and understandable, not to claim an automated procurement service.

Path to useful change

A practical version would need approved data access, leakage checks, meaningful baselines, human review, error analysis and measurement against a real process. Separate process-improvement work is not presented as an outcome of this synthetic model.

Evidence boundary: The public account shows the method and intended decision. No workplace transactions, supplier details or internal process documents are published.

A CLOSER LOOK

Explore the constructed patterns. Original synthetic procurement notebook output. These groups reflect the generated dataset, not real suppliers or teams. — Original synthetic procurement notebook output. These groups reflect the generated dataset, not real suppliers or teams.

An unusual score is a question. Original synthetic procurement notebook output. An anomaly score does not establish fraud, misconduct or a faulty transaction. — Original synthetic procurement notebook output. An anomaly score does not establish fraud, misconduct or a faulty transaction.

CONTINUE EXPLORINGCapstone study ↗Use-case method ↗

Try the Smart Procurement Lab.

Four explainable prototypes: PO delay · Approval bottlenecks · Anomaly review · Carbon impact. Change fictional inputs, compare scenarios and inspect measured synthetic-test results.

EXPLAINABLE AI & DATA / READ THE METHOD

Read the evidence, understand the method.

A guide to the charts and case evidence on this page. Exhibit captions remain the authority for data origin and the claims each visual supports.

Follow the reasoning.

SourceRead the exhibit’s evidence label
RepresentInspect units, categories and scales
CompareDistinguish observed results from demonstrations
ReviewCheck limitations before taking action

Explore the building blocks.

AI Capability4

AI/Data Concepts2

Data Science Pipeline1

Evaluation & XAI3

Python Package2

Responsible AI1

Visualisation1

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

Explore the explanation matrix · 14 concepts

Concept categoryFind a term or example

14 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
Visual encodingVisualisation	Mapping values or categories to marks, position, length, colour and labels.Primary reference ↗	Make the comparison visible, with a scale and a clear label.	Published analysis Read axis labels, denominators and captions before comparing exhibits.
Synthetic dataAI/Data Concepts	Generated records used to represent scenarios rather than directly report observed individuals or events.Primary reference ↗	A practice dataset. Useful for demonstration, not proof of workplace impact.	Demonstration Exhibits labelled synthetic or reconstructed illustrate methods; they are not disclosed workplace records.
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.	Published analysis Counts and trend summaries describe the stated records and period, not future performance.
Residuals and prediction errorEvaluation & XAI	A residual compares an observed value with its fitted or predicted value. Error metrics summarise those discrepancies.Primary reference ↗	How far did the estimate miss, and where does it miss most?	Learning context Prediction exhibits can compare observed and estimated values; a smooth chart alone is not validation.
Confusion matrix, precision and recallEvaluation & XAI	A confusion matrix counts predicted versus actual classes. Precision measures positive-result reliability; recall measures positive-case coverage.Primary reference ↗	Which alarms were right, which were false, and which cases were missed?	Learning context Where a confusion chart is shown, inspect false alarms and missed cases as well as correct predictions.
Data science pipelineData Science Pipeline	An ordered, reproducible sequence for acquiring, validating, preparing, analysing and evaluating data.Primary reference ↗	A chain from a question and source to an answer someone can check.	Published analysis Case studies connect the problem, evidence, preparation, method, evaluation and decision.
Explanation versus causal proofEvaluation & XAI	A model explanation describes selected behaviour or contributions; it does not establish causal effects or full reliability.Primary reference ↗	A reason for this output is useful, but it is not proof that the model is right.	Responsible use A persuasive visual does not prove causation or transferability.
Data minimisationResponsible AI	Limit collected, disclosed and retained information to what is needed for the stated purpose.Primary reference ↗	Use the smallest appropriate amount of information.	Responsible use Restricted source records stay private; approved aggregates and labelled reconstructions support public learning.
pandasPython Package	A Python library for labelled tabular data manipulation and analysis.Primary reference ↗	A programmable workbench for cleaning and comparing tables.	Learning context A common Python option for tabular preparation; its inclusion is not a claim that this browser runs pandas.
MatplotlibPython Package	A Python plotting library for static, animated and interactive visualisations.Primary reference ↗	Turn numerical work into labelled figures that can be inspected and shared.	Learning context A common way to prepare Python figures. This page displays published assets rather than launching Python plotting sessions.
Machine learning (ML)AI Capability	Methods that estimate patterns or parameters from examples to support inference on other inputs.Primary reference ↗	Learn a pattern from examples, then check whether it helps with new ones.	Learning context ML learns from examples. Read the page-specific methods below to see whether any model runs here.
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 Deep learning is an AI capability, not a label for every chart. No deep model is implied by this explanation panel.
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.	Learning context Text search, translation, thematic classification and generation are different language tasks; their implementation is identified separately.
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 Sentiment estimates expressed tone. It must not be confused with topic classification or a diagnosis of a person.