---
title: Jumps and Margin Level Study
url: https://www.ml-quant.com/papers/repec/taf-reroxx-v-36-y-2023-i-2-p-2136228/
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: RePEc:taf:reroxx:v:36:y:2023:i:2:p:2136228
source_url: https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fhdl.handle.net%2F10.1080%2F1331677X.2022.2136228%3Bh%3Drepec%3Ataf%3Areroxx%3Av%3A36%3Ay%3A2023%3Ai%3A2%3Ap%3A2136228
featured: 2024-03-20
citations: unknown
topic: Econometrics & Forecasting
---


# Jumps and Margin Level Study

The SE-SVCJ model, combined with a GPD, provides a more accurate forecast of margin levels in the stock index futures market.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fhdl.handle.net%2F10.1080%2F1331677X.2022.2136228%3Bh%3Drepec%3Ataf%3Areroxx%3Av%3A36%3Ay%3A2023%3Ai%3A2%3Ap%3A2136228
- Identifier: RePEc:taf:reroxx:v:36:y:2023:i:2:p:2136228
- Released: 2023-05-23
- First featured: Quant Letter No. 41 (2024-03-20): https://www.ml-quant.com/issues/2024-03-20/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [TKAN: Temporal Kolmogorov-Arnold Networks](https://www.ml-quant.com/papers/ssrn/4825654/): The article presents Temporal Kolomogorov-Arnold Networks (TKANs), a new neural network design that merges the benefits of Recurrent Neural Networks and Long Short-Term Memory for improved multistep time series forecasting.
- [Robust agents learn causal world models](https://www.ml-quant.com/papers/arxiv/2402.10877/): The research suggests that intelligent agents must learn an approximate causal model to generalize to new domains, impacting fields like transfer learning and causal inference.
- [TS-RSR: A Provably Efficient Approach for Batch Bayesian Optimization](https://www.ml-quant.com/papers/arxiv/2403.04764/): A novel method for batch Bayesian Optimization (BO) is introduced, which reduces redundancy and focuses on points with high predictive means or uncertainty, showing superior performance on nonconvex test functions.
- [Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues](https://www.ml-quant.com/papers/arxiv/2307.11888/): The study reveals that deep neural networks using linear complex-valued RNNs and MLPs can accurately approximate regular causal sequence-to-sequence maps, with complex eigenvalues near unit disk aiding in information storage.
- [Supervised autoencoder MLP for financial time series forecasting](https://www.ml-quant.com/papers/arxiv/2404.01866/): The study investigates the use of supervised autoencoders in improving financial forecasting through precise parameter tuning.
- [Regularization for electricity price forecasting](https://www.ml-quant.com/papers/arxiv/2404.03968/): The study reveals that LQ and elastic net penalty functions provide more precise electricity price predictions than other methods, including the popular LASSO. It also confirms that cross-validation is a useful tool for optimizing parameters.