| 1. |
- Cortese, Federico P., et al.
(author)
-
What drives cryptocurrency returns? A sparse statistical jump model approach
- 2023
-
In: Digital Finance. - 2524-6984.
-
Journal article (peer-reviewed)abstract
- We apply the statistical sparse jump model, a recently developed, interpretable and robust regime-switching model, to infer key features that drive the return dynamics of the largest cryptocurrencies. The algorithm jointly performs feature selection, parameter estimation, and state classification. Our large set of candidate features are based on cryptocurrency, sentiment and financial market-based time series that have been identified in the emerging literature to affect cryptocurrency returns, while others are new. In our empirical work, we demonstrate that a three-state model best describes the dynamics of cryptocurrency returns. The states have natural market-based interpretations as they correspond to bull, neutral, and bear market regimes, respectively. Using the data-driven feature selection methodology, we are able to determine which features are important and which ones are not. In particular, out of the set of candidate features, we show that first moments of returns, features representing trends and reversal signals, market activity and public attention are key drivers of crypto market dynamics.
|
|
| 2. |
- Nystrup, Peter, et al.
(author)
-
Feature selection in jump models
- 2021
-
In: Expert Systems with Applications. - : Elsevier BV. - 0957-4174. ; 184
-
Journal article (peer-reviewed)abstract
- Jump models switch infrequently between states to fit a sequence of data while taking the ordering of the data into account We propose a new framework for joint feature selection, parameter and state-sequence estimation in jump models. Feature selection is necessary in high-dimensional settings where the number of features is large compared to the number of observations and the underlying states differ only with respect to a subset of the features. We develop and implement a coordinate descent algorithm that alternates between selecting the features and estimating the model parameters and state sequence, which scales to large data sets with large numbers of (noisy) features. We demonstrate the usefulness of the proposed framework by comparing it with a number of other methods on both simulated and real data in the form of financial returns, protein sequences, and text. By leveraging information embedded in the ordering of the data, the resulting sparse jump model outperforms all other methods considered and is remarkably robust to noise.
|
|
| 3. |
- Nystrup, Peter, et al.
(author)
-
Greedy Online Classification of Persistent Market States Using Realized Intraday Volatility Features
- 2020
-
In: The Journal of Financial Data Science. - : Pageant Media US. - 2640-3943. ; 2:3, s. 25-39
-
Journal article (peer-reviewed)abstract
- In many financial applications, it is important to classify time-series data without any latency while maintaining persistence in the identified states. The authors propose a greedy online classifier that contemporaneously determines which hidden state a new observation belongs to without the need to parse historical observations and without compromising persistence. Their classifier is based on the idea of clustering temporal features while explicitly penalizing jumps between states by a fixed-cost regularization term that can be calibrated to achieve a desired level of persistence. Through a series of return simulations, the authors show that in most settings their new classifier remarkably obtains a higher accuracy than the correctly specified maximum likelihood estimator. They illustrate that the new classifier is more robust to misspecification and yields state sequences that are significantly more persistent both in and out of sample. They demonstrate how classification accuracy can be further improved by including features that are based on intraday data. Finally, the authors apply the new classifier to estimate persistent states of the S&P 500 Index.
|
|
