<
← Back to The IndexFinal ReviewGroup 5
Final Review

Review Nº 05

What Drives the Location of Data Centres in Europe? An Empirical Analysis at the NUTS3 Level
AuthorsLi Zechang, Fan Xinrui, Wang Junyi, Fan Zixuan
25/30
Score
The report is concise and interpretable with useful OLS findings, but it under-emphasizes the required binary classification task and relies too heavily on in-sample regression performance.
Data Centres · Final Review

The Pros

1 Item
+
Clear hypotheses; understandable OLS model progression; good discussion of GDP, IXP count, electricity price, and latency; recognizes the training/test performance gap; notes missing temperature, unobserved policy variables, and extreme hubs; Random Forest feature importance supports the main finding.

The Cons

1 Item
−
The project requested an explainable logistic model plus most accurate model for location presence, but this submission focuses mainly on count regression; OLS R² is compared to RF test R² in a non-equivalent way; no cross-validation is reported; model evaluation is thin; data collection and preprocessing details are minimal; uncertainty and robustness checks are limited.
↩ Back to The Index
Final Review · Group 5The IndexData Centres · 2026