Exploring determinants of network stochastic dominance ratios: a causal approach using explainable AI
A new study introduces the network stochastic dominance ratio (NetSDR), a tool for ranking investments across stocks, commodities, and cryptocurrencies. The research finds that risk metrics like Expected Shortfall and Maximum Drawdown, plus distributional features such as Kurtosis, influence asset rankings more than average returns. Using machine learning (XGBoost) and explainable AI, the authors reveal these drivers. While XGBoost outperforms traditional methods, the study is limited by its narrow asset selection and time frame.
What it examines
This paper uses structural causal modeling, machine learning (XGBoost), and explainable AI (SHAP) to study what factors influence the network stochastic dominance ratio in investment portfolios. It aims to identify key performance and risk metrics that determine asset dominance, improving asset selection and portfolio management.
What it concludes
The study finds that risk metrics like Expected Shortfall and Max Drawdown are more important than average returns for asset dominance. This helps investors choose assets more effectively. Applications include smarter portfolio construction and risk management. Future research should expand asset classes and test more machine learning methods.
Evidence objects
The study introduces NetSDR, a dynamic, time-sensitive measure, and combines structural causal modeling, XGBoost, and SHAP to transparently identify what truly influences asset rankings, offering a fresh, interpretable framework for investors.
key_findings bullet 2 · key_findings · validation V0
Risk metrics like Expected Shortfall, Maximum Drawdown, and Kurtosis outweigh average returns in asset dominance, overturning traditional finance beliefs and revealing surprising new drivers for investment ranking across stocks, commodities, and cryptocurrencies.
key_findings bullet 1 · key_findings · validation V0
Using daily returns from 19 assets, XGBoost outperforms quantile regression in predicting NetSDR, but the research is limited by narrow asset classes and time windows, suggesting future expansion and exploration of more machine learning techniques.
key_findings bullet 3 · key_findings · validation V0
This paper uniquely synthesizes stochastic dominance, machine learning, and explainable AI (XAI) within a causality-driven framework for portfolio optimization. Its originality lies in combining structural causal modeling and SHAP to interpret determinants of network stochastic dominance ratios, offering practical relevance, interpretability, and empirical validationmaking it compelling for quantitative finance and AI-driven asset selection.
key_findings bullet 4 · key_findings · validation V0
Raw abstract and provenance
- … true causal mechanisms that determine financial ratios and investment decisions. Moreover, despite the extensive research on financial ratios analysis and asset ranking, …
Source row: 763 · abstract type: snippet