2498. Rank-Size Analysis of Optimal Portfolio Weights Across Portfolio Optimization Models
Invited abstract in session TB-9: Complexity in finance, stream OR in Finance and Insurance .
Tuesday, 10:30-12:00Room: Clarendon SR 2.01
Authors (first author is the speaker)
| 1. | Valerio Ficcadenti
|
| Business School, London South Bank University | |
| 2. | Alessio Di Paolo
|
| Business Studies, Roma Tre University | |
| 3. | Francesco Cesarone
|
| Department of Business Studies, Roma Tre University | |
| 4. | Roy Cerqueti
|
| Department of Social and Economic Sciences, Sapienza University of Rome |
Abstract
Portfolio optimisation has been widely studied, yet a unified framework for comparing optimal portfolio weight distributions across rank-size models remains unexplored. We introduce a rank-size analysis approach to systematically characterise these distributions in portfolio optimisation models.
Four portfolio selection strategies—Mean-Variance, Conditional Value-at-Risk, Most Diversified, and Risk Parity—are analysed across the constituents of major financial indices (e.g., FTSE 100) over the period 2009–2023. The resulting empirical distributions of optimal weights are modelled using various rank-size functions, including the Exponential Law, Discrete Generalised Beta Distribution, and the Universal Law. By fitting these functions to weight distributions, we extract insights into the concentration patterns of portfolios, enabling the comparison of different strategies based on allocation ranks.
To determine the most representative rank-size function, we introduce a selection methodology based on stochastic dominance, applied to the RMSE distribution of best-fit series. This approach ensures that the chosen function minimises average error while remaining robust across various quantiles of the weight distribution. The findings suggest that certain rank-size laws consistently outperform others in capturing the underlying structure of optimal portfolio weights, offering a novel lens through which to evaluate and compare portfolio construction strategies.
Keywords
- Finance and Banking
- Financial Modelling
- Analytics and Data Science
Status: accepted
Back to the list of papers