# STRAPSim: A Portfolio Similarity Metric for ETF Alignment and Portfolio Trades

arXiv: https://arxiv.org/abs/2509.24151 · HTML: https://mlsanity.com/paper/2509.24151/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Further Generalizations of the Jaccard Index](https://mlsanity.com/paper/2110.09619/) (2021)
- [Fund2Vec: Mutual Funds Similarity using Graph Learning](https://mlsanity.com/paper/2106.12987/) (2021)
- [Quantifying Outlierness of Funds from their Categories using Supervised Similarity](https://mlsanity.com/paper/2308.06882/) (2023)
- [Enhanced Local Explainability and Trust Scores with Random Forest Proximities](https://mlsanity.com/paper/2310.12428/) (2023)
- [Can an unsupervised clustering algorithm reproduce a categorization system?](https://mlsanity.com/paper/2408.10340/) (2024)

## Built on by (most cited first, 1 of 1)

- [The Generalized Proximity Forest](https://mlsanity.com/paper/2511.19487/) (2025)

## Abstract (arXiv)

Accurately measuring portfolio similarity is critical for a wide range of financial applications, including Exchange-traded Fund (ETF) recommendation, portfolio trading, and risk alignment. Existing similarity measures often rely on exact asset overlap or static distance metrics, which fail to capture similarities among the constituents (e.g., securities within the portfolio) as well as nuanced relationships between partially overlapping portfolios with heterogeneous weights. We introduce STRAPSim (Semantic, Two-level, Residual-Aware Portfolio Similarity), a novel method that computes portfolio similarity by matching constituents based on semantic similarity, weighting them according to their portfolio share, and aggregating results via residual-aware greedy alignment. We benchmark our approach against Jaccard, weighted Jaccard, as well as BERTScore-inspired variants across public classification, regression, and recommendation tasks, as well as on corporate bond ETF datasets. Empirical results show that our method consistently outperforms baselines in predictive accuracy and ranking alignment, achieving the highest Spearman correlation with return-based similarity. By leveraging constituent-aware matching and dynamic reweighting, portfolio similarity offers a scalable, interpretable framework for comparing structured asset baskets, demonstrating its utility in ETF benchmarking, portfolio construction, and systematic execution.