Ibraheem Wagih · Fraud & Financial Crime → Analytics
Projects / MSc Dissertation

Clustering WiFi Telemetry into Failure Archetypes

Individual MSc Dissertation · Industry partnership UCL MSc Business Analytics

To what extent can unsupervised clustering of WiFi telemetry identify distinct home-gateway failure archetypes, and how should ISPs prioritise them for proactive intervention? An industry dissertation with a WiFi analytics scaleup. This page describes my approach and method only. All partner data, figures and findings are withheld under the project's confidentiality terms.

Unsupervised
clustering, no hand-labelled fault data
2-stage
design: healthy vs degraded, then archetypes
3-way
validation: internal, external and temporal

Problem

ISPs mostly discover in-home WiFi problems reactively, through helpline calls, engineer dispatches and churn. Existing proactive systems detect that a gateway is degrading but not how: a router hidden behind a television needs repositioning, a home saturated by neighbouring networks can be fixed remotely by band steering, a boot-looping gateway needs replacing. Treating those as one "degraded" population wastes intervention budget. The missing step is typing: segmenting degraded gateways into recognisable failure archetypes, each mapped to a feasible remediation route, without any hand-labelled fault data.

Approach

A cross-sectional weekly snapshot rather than a pooled panel, because the weekly fields are rolling seven-day windows and pooling daily exports would duplicate each record into near-identical rows, inflating the apparent sample. The pipeline runs data triage with an audit trail, leakage prevention, feature engineering over mixed telemetry, then dimensionality reduction with PCA. Stage one clusters the full population to separate healthy from degraded. Stage two re-fits on the degraded population alone and re-clusters it, letting failure types emerge without the healthy mass as a confound. K-Means with k-means++ initialisation runs against a Gaussian Mixture Model comparator, with DBSCAN excluded on methodological grounds.

Validation Before Interpretation

Internal validity uses Silhouette and Davies-Bouldin scores across candidate cluster counts, computed on a fixed, seeded subsample because Silhouette's quadratic cost is prohibitive at full scale. External validity checks cluster assignments against an operational quality-of-experience label that the clustering never saw, using Adjusted Rand Index and Normalised Mutual Information. Temporal stability re-runs the assignment on a later snapshot to test whether archetypes persist. Clusters are treated as hypotheses to be validated, not answers.

Findings

The clustering recovers a small set of stable, interpretable failure archetypes with distinct remediation routes, validated externally and over time. Under the project's confidentiality terms, all figures, statistics and archetype detail are withheld from this page. The full dissertation may be available on request where confidentiality allows.