---
title: Forecasting with machine learning Shadow-Rate VARs
url: https://www.ml-quant.com/papers/ssrn/4828070/
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 4828070
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4828070
featured: 2024-05-15
citations: 1
topic: Econometrics & Forecasting
---


# Forecasting with machine learning Shadow-Rate VARs

The article examines the use of Shadow Rate Vector Autoregressions in macroeconomic forecasting, particularly the effects of shrinkage priors.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4828070
- Identifier: SSRN 4828070
- Released: 2024-05-14
- First featured: Quant Letter No. 49 (2024-05-15): https://www.ml-quant.com/issues/2024-05-15/
- Citations (Semantic Scholar): 1
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [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.
- [Interpretive Earnings Forecasts via Machine Learning: A High-Dimensional Financial Statement Data Approach](https://www.ml-quant.com/papers/ssrn/4619313/): Using machine learning models and comprehensive Compustat financial statement data for earnings forecasting can yield predictions that are up to 13% more accurate than traditional linear approaches.
- [Online Multivariate Regularized Distributional Regression for High-dimensional Probabilistic Electricity Price Forecasting](https://www.ml-quant.com/papers/arxiv/2504.02518/): The study introduces a faster, more accurate online model for predicting electricity prices.
- [Mean-Field Microcanonical Gradient Descent](https://www.ml-quant.com/papers/arxiv/2403.08362/): The study presents a new model that improves the efficiency of sampling multiple data points simultaneously, particularly in high-dimensional financial time series.
- [Clustering Zero-Inflated Time Series](https://www.ml-quant.com/papers/repec/spr-jclass-v-40-y-2023-i-2-d-10-1007-s00357-023-09437-z/): A novel clustering method for high-dimensional zero-inflated time series data has been developed, utilizing a modified thick-pen transform and an efficient iterative clustering algorithm, proven effective through simulations and real datasets.
- [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.