Carbon Price Forecasting with Quantile Regression and Feature Selection

ArXiv ID: 2305.03224 “View on arXiv”

Authors: Unknown

Abstract

Carbon futures has recently emerged as a novel financial asset in the trading markets such as the European Union and China. Monitoring the trend of the carbon price has become critical for both national policy-making as well as industrial manufacturing planning. However, various geopolitical, social, and economic factors can impose substantial influence on the carbon price. Due to its volatility and non-linearity, predicting accurate carbon prices is generally a difficult task. In this study, we propose to improve carbon price forecasting with several novel practices. First, we collect various influencing factors, including commodity prices, export volumes such as oil and natural gas, and prosperity indices. Then we select the most significant factors and disclose their optimal grouping for explainability. Finally, we use the Sparse Quantile Group Lasso and Adaptive Sparse Quantile Group Lasso for robust price predictions. We demonstrate through extensive experimental studies that our proposed methods outperform existing ones. Also, our quantile predictions provide a complete profile of future prices at different levels, which better describes the distributions of the carbon market.

Keywords: Carbon Futures, Price Forecasting, Sparse Quantile Group Lasso, Time-series Prediction, Commodities

Complexity vs Empirical Score

• Math Complexity: 7.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Holy Grail
• Why: The paper uses advanced statistical methods like quantile regression, sparse group lasso, and adaptive lasso with significant mathematical notation and derivations. It also demonstrates empirical rigor through ’extensive experimental studies’ on real-world carbon markets (EU and Guangzhou) with feature selection and performance comparison against benchmarks.

  flowchart TD
    Goal["Research Goal:<br>Improve Carbon Price Forecasting"]
    Inputs["Data Inputs:<br>Commodity Prices, Export Volumes,<br>Prosperity Indices"]
    Method["Methodology:<br>Feature Selection &<br>Sparse Quantile Group Lasso"]
    Process["Computational Process:<br>Model Training &<br>Multi-Quantile Prediction"]
    Outcomes["Key Outcomes:<br>1. Superior Forecast Accuracy<br>2. Complete Price Distribution Profile"]

    Goal --> Inputs
    Inputs --> Method
    Method --> Process
    Process --> Outcomes