---
title: Regime-Dependent Dependence: Cryptocurrencies and Traditional Assets Under Structural Breaks
url: https://www.ml-quant.com/papers/repec/hal-journl-hal-05752791/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-16
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:hal:journl:hal-05752791
source_url: https://econpapers.repec.org/RePEc:hal:journl:hal-05752791
featured: 2026-10-16
citations: unknown
topic: Crypto & DeFi
---


# Regime-Dependent Dependence: Cryptocurrencies and Traditional Assets Under Structural Breaks

The study proposes a multi-stage method combining neural networks and copulas to detect regime changes and finds cryptocurrency dependence with traditional assets increases sharply during crises.

- Source: https://econpapers.repec.org/RePEc:hal:journl:hal-05752791
- Identifier: RePEc:hal:journl:hal-05752791
- Released: 2026-10-12
- First featured: Quant Letter No. 135 (2026-10-16): https://www.ml-quant.com/issues/2026-10-16/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Crypto & DeFi
- Authors: Virginie Terraza, Aslı Boru İpek

## Related

- [Deep Learning for High-Frequency Cryptocurrency Trend Detection: Incorporating Technical Indicators and A New Approach For Data Stationarity](https://www.ml-quant.com/papers/ssrn/4796336/): The research presents a new data preprocessing technique and a Convolutional Neural Networks (CNN) model for predicting Bitcoin market trends using 15-minute candlestick data.
- [Neural Hawkes: non-parametric estimation in high dimension and causality analysis in cryptocurrency markets](https://www.ml-quant.com/papers/arxiv/2401.09361/): High Dimension Non-Parametric Estimation: A new method called the moment-based neural Hawkes estimation method has been developed to analyze the microstructure of cryptocurrency markets, using neural networks to solve partial differential equations.
- [Transformer-based approach for Ethereum Price Prediction Using Crosscurrency correlation and Sentiment Analysis](https://www.ml-quant.com/papers/arxiv/2401.08077/): The research uses a transformer-based neural network to forecast Ethereum prices, indicating a strong correlation with other cryptocurrencies and sentiments, and suggests a theory on sentiment-driven illusion of causality in cryptocurrency price movements.
- [Factors Influencing Cryptocurrency Prices: Evidence from Bitcoin, Ethereum, Dash, Litcoin, and Monero](https://www.ml-quant.com/papers/arxiv/2511.22782/): The study examines the price factors influencing five major cryptocurrencies from 2010-2018, highlighting the roles of market conditions, long-term appeal, and the SP500 index.
- [The Impact of Bitcoin ETF Approval on Bitcoin's Hedging Properties Against Traditional Assets](https://www.ml-quant.com/papers/arxiv/2512.12815/): Changing Dynamics with Traditional Assets: In January 2024, the approval of a Bitcoin Spot ETF boosted interest from big investors and made Bitcoin more closely linked to stock markets, while its connections to gold remained steady and its relationship with the U.S. Dollar stayed negative.
- [Improving Cryptocurrency Pump-and-Dump Detection through Ensemble-Based Models and Synthetic Oversampling Techniques](https://www.ml-quant.com/papers/arxiv/2510.00836/): The study uses SMOTE and advanced ensemble learning models like XGBoost and LightGBM to effectively detect pump and dump manipulation in cryptocurrency markets, enhancing market transparency and stability.