University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
A Data-Driven model for financially viable fiber-optic network expansion at KPN
Lubbers, L.H. (2025) A Data-Driven model for financially viable fiber-optic network expansion at KPN.
|
PDF
5MB |
| Abstract: | KPN has rapidly expanded its fiber-optic network across the Netherlands, yet many buildings—especially high-rise and duplex properties—remain unconnected. As KPN shifts from rapid roll-out to maximizing customer connections and capital efficiency, it needs a more granular, transparent selection approach. Currently, decisions rely on the previous selection model, which predicts area-level returns but lacks building-level cost and customer insights, leading to manual interpretation and suboptimal capital allocation. This thesis, conducted with KPN’s Fiber Connect Planning & Capacity team, develops a data-driven method to prioritize financially viable buildings. It integrates machine learning predictions of customer uptake, routing-based cost heuristics, and feasibility checks for constraints like demolition risk and overbuild. The combined score ranks buildings, which are clustered into coherent projects, supporting practical planning. Sensitivity analyses confirm the robustness of the method under different assumptions. Trained on KPN data, the predictive model achieves a macro F1 score of 0.65 and an AUC of 0.67, outperforming baselines. Cost experiments show trench routes average 27% longer than straight lines, and multi-unit buildings reduce per-address costs, aligning with historical data. The approach is implemented in a Power BI tool for planners. Beyond practical benefits, this study contributes a replicable framework for brownfield network prioritization, with potential applications in other utility sectors. |
| Item Type: | Essay (Master) |
| Clients: | KPN, Amersfoort, Netherlands |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 58 process technology, 83 economics |
| Programme: | Industrial Engineering and Management MSc (60029) |
| Link to this item: | https://purl.utwente.nl/essays/107695 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page