Accurate prediction of carbon prices is crucial for a stable market, enabling informed decision-making and
strategic planning. Over the years, several models for predicting carbon prices have been proposed to enhance
accuracy. However, previous research has primarily focused on improving accuracy, often neglecting the
importance of making the findings understandable and meaningful. This paper aims to bridge that gap by not
only improving prediction accuracy but also ensuring that the results are transparent and comprehensible, thus
contributing to more effective and informed decision-making in the carbon market. An optimized Long Short-
Term Memory (LSTM) network enhanced with the modified light spectrum optimizer (MLSO) is proposed to
improve carbon price prediction accuracy. Additionally, the paper incorporates Explainable AI (XAI) techniques
to interpret the results, bridging the gap between accuracy and interpretability. The proposed model is evaluated
on carbon price historical transaction data acquired from Investing.com and tested on eight other benchmark
datasets with different characteristics. The proposed model achieved 0.66 root mean square error (RMSE), 0.99
R
, 0.37 mean absolute error (MAE), 0.15 mean absolute percentage error (MAPE), and 0.44 mean square error
(MSE). The results showed that low price, high price, and open price features have the highest significance in
driving the model's predictions in comparison to other features like date, volume, and price change features.
Additionally, the results indicate that the year, day, and month do not significantly influence the carbon price.
The proposed model outperforms state-of-the-art models and other well-known machine learning algorithms
according to the experimental results. Moreover, the results indicate that the predictive capability of the pro
posed model serves as a valuable tool for investors and carbon traders to understand the factors influencing price
changes, optimize their strategies, and minimize risk |
