# Can an unsupervised clustering algorithm reproduce a categorization system?

arXiv: https://arxiv.org/abs/2408.10340 · HTML: https://mlsanity.com/paper/2408.10340/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 45 references that are in the map.
- First posted on arXiv 19 Aug 2024.

## Builds on (most cited first, 8 of 8)

- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [Geometry- and Accuracy-Preserving Random Forest Proximities](https://mlsanity.com/paper/2201.12682/) (2022)
- [metric-learn: Metric Learning Algorithms in Python](https://mlsanity.com/paper/1908.04710/) (2019)
- [Quantifying Outlierness of Funds from their Categories using Supervised Similarity](https://mlsanity.com/paper/2308.06882/) (2023)
- [Machine Learning Fund Categorizations](https://mlsanity.com/paper/2006.00123/) (2020)
- [Open Set Recognition for Random Forest](https://mlsanity.com/paper/2408.02684/) (2024)
- [Quantile Regression using Random Forest Proximities](https://mlsanity.com/paper/2408.02355/) (2024)
- [Case-based Explainability for Random Forest: Prototypes, Critics, Counter-factuals and Semi-factuals](https://mlsanity.com/paper/2408.06679/) (2024)

## Built on by (most cited first, 2 of 2)

- [STRAPSim: A Portfolio Similarity Metric for ETF Alignment and Portfolio Trades](https://mlsanity.com/paper/2509.24151/) (2025)
- [Toward precision soil health: A regional framework for site-specific management across Missouri](https://mlsanity.com/paper/2510.26815/) (2025)

## Abstract (arXiv)

Peer analysis is a critical component of investment management, often relying on expert-provided categorization systems. These systems' consistency is questioned when they do not align with cohorts from unsupervised clustering algorithms optimized for various metrics. We investigate whether unsupervised clustering can reproduce ground truth classes in a labeled dataset, showing that success depends on feature selection and the chosen distance metric. Using toy datasets and fund categorization as real-world examples we demonstrate that accurately reproducing ground truth classes is challenging. We also highlight the limitations of standard clustering evaluation metrics in identifying the optimal number of clusters relative to the ground truth classes. We then show that if appropriate features are available in the dataset, and a proper distance metric is known (e.g., using a supervised Random Forest-based distance metric learning method), then an unsupervised clustering can indeed reproduce the ground truth classes as distinct clusters.