---
title: Cumulant Risk Premium: A New Methodology
url: https://www.ml-quant.com/papers/ssrn/4597367/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4597367
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4597367
featured: 2023-10-12
citations: unknown
topic: Asset Pricing & Factors
---


# Cumulant Risk Premium: A New Methodology

A New Methodology: A new method measures the risk premium of higher-order cumulants using leveraged ETFs, showing significant differences across asset classes, especially during stressful times.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4597367
- Identifier: SSRN 4597367
- Released: 2023-01-19
- First featured: Quant Letter No. 20 (2023-10-12): https://www.ml-quant.com/issues/2023-10-12/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Asset Pricing & Factors

## Related

- [Expanding the Fama–French Factor Model with the Industry Beta](https://www.ml-quant.com/papers/ssrn/4528675/): The news-based stock pricing model (NBSPM) performs better than the five-factor Fama-French model (FF5M) for US equity sector ETFs, but adding industry beta to FF5M improves its accuracy, though not as much as NBSPM.
- [Economic Uncertainty & the Beta Anomaly](https://www.ml-quant.com/papers/ssrn/4684356/): The beta-alpha anomaly only occurs during times of low economic uncertainty, with retail investors and active mutual funds more prone to pursue high-beta securities.
- [Machine Learning Asset Pricing](https://www.ml-quant.com/papers/ssrn/5193994/): The article forecasts the prices of financial innovation-themed ETFs using machine learning, finding that ARIMA and Prophet models perform better than LSTM for shorter datasets.
- [A Deep Structural Model for Empirical Asset Pricing](https://www.ml-quant.com/papers/ssrn/4602537/): ML and Theory Integration: The article introduces a new model that merges deep learning and structural models for better prediction of equity returns and covariances, leading to higher returns and sharpe ratios.
- [Generalized Autoregressive Conditional Betas: A New Multivariate Score-Driven Filter](https://www.ml-quant.com/papers/ssrn/4602060/): New: A new asset pricing model, the generalized ACB, is introduced, enhancing the autoregressive conditional beta model by driving dynamic interaction effects among beta coefficients.
- [Dynamic Time Warping for Lead-Lag Relationships in Lagged Multi-Factor Models](https://www.ml-quant.com/papers/arxiv/2309.08800/): A new technique using dynamic time warping has been created to identify lead-lag relationships in multivariate time series systems, demonstrated in financial markets.