Global smart cities classification using a machine learning approach to evaluating livability, technology, and sustainability performance across key urban indices
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Smart cities have become an increasingly important response to urbanization challenges, integrating technology to enhance city infrastructure, services, and sustainability. This study aims to classify the highest 50 global smart cities based on key livability and technology indices, using advanced machine learning (ML) models to assess city performance comprehensively. The necessity of this research lies in its focus on identifying patterns and best practices among high-performing cities, offering actionable insights for urban planners and policymakers aiming to improve smart city initiatives. This approach is necessary for understanding and replicating best practices in urban management and smart city development. Focusing on high-ranking cities ensures the study analyzes robust and reliable data, avoiding noise and inconsistencies arising from lower-performing or less-documented cases. Drawing on data from the Smart Cities Index (SCI) and other economic and sustainability competitiveness metrics, the study uses various ML algorithms to categorize cities into performance classes, ranging from high-achieving Class 1 to emerging Class 3 cities. The methodology involves data preparation with imputation and normalization, followed by training 9 supervised ML models. The results show that Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Decision Tree are identified as the most effective classifiers. Furthermore, the results indicate that cities with well-integrated governance, infrastructure, and sustainability practices consistently rank higher, while cities in the lower classes face challenges in these areas. Policy implications suggest that cities aiming to enhance their smart city performance should prioritize comprehensive urban management strategies that balance technological infrastructure with sustainability and public service accessibility to drive more equitable and resilient urban growth. • Classifies smart cities to boost livability and sustainability. • Uses Smart Cities Index to assess global city performance. • Tests 9 supervised and 2 unsupervised models for classification. • Support vector machine model achieves 93 % accuracy in smart city classification. • Top cities excel in governance, infrastructure, and services.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it