Search results

This study investigates clean energy, commodities, green bonds and environmental, social and governance (ESG) index prices forecasting and assesses the predictive performance of various factors on these asset prices, used for the development of a robust forecasting support decision model using machine learning (ML) techniques. More specifically, we explore the impact of the financial stress on forecasting price.

We utilize feature selection techniques to evaluate the predictive efficacy of various factors on asset prices. Moreover, we have developed a forecasting model for these asset prices by assessing the accuracy of two ML models: specifically, the deep learning long short-term memory (LSTM) neural networks and the extreme gradient boosting (XGBoost) model. To check the robustness of the study results, the authors referred to bootstrap linear regression as an alternative traditional method for forecasting green asset prices.

The results highlight the significance of financial stress in enhancing price forecast accuracy, with the financial stress index (FSI) and panic index (PI) emerging as primary determinants. In terms of the forecasting model's accuracy, our analysis reveals that the LSTM outperformed the XGBoost model, establishing itself as the most efficient algorithm among the two tested.

This research enhances comprehension, which is valuable for both investors and policymakers seeking improved price forecasting through the utilization of a predictive model.

To the authors' best knowledge, this marks the inaugural attempt to construct a multivariate forecasting model. Indeed, the development of a robust forecasting model utilizing ML techniques provides practical value as a decision support tool for shaping investment strategies.

In this paper, the authors investigate the impact of the confirmation bias on returns, expectations and hedging of optimistic and pessimistic traders in the cryptocurrencies, commodities and stock markets before and during COVID-19 periods.

The authors investigate the impact of the confirmation bias on the estimated returns and the expectations of optimistic and pessimistic traders by employing the financial stochastic model with confirmation bias. Indeed, the authors compute the optimal portfolio weights, the optimal hedge ratios and the hedging effectiveness.

The authors find that without confirmation bias, during the two sub periods, the expectations of optimistic and pessimistic trader’s seem to convergence toward zero. However, when confirmation bias is particularly strong, the average distance between these two expectations are farer. The authors further show that, with and without confirmation bias, the optimal weights (the optimal hedge ratios) are found to be lower (higher) for all pairs of financial market during the COVID-19 period as compared to the pre-COVID-19 period. The authors also document that the stronger the confirmation bias is, the lower the optimal weight and the higher the optimal hedge ratio. Moreover, results reveal that the values of the optimal hedge ratio for optimistic and pessimistic traders affected or not by the confirmation bias are higher during the COVID-19 period compared to the estimates for the pre-COVID period and inversely for the optimal hedge ratios and the hedging effectiveness index. Indeed, either for optimists or pessimists, the presence of confirmation bias leads to higher optimal hedge ratio, higher optimal weights and higher hedging effectiveness index.

The findings of the study provided additional evidence for investors, portfolio managers and financial analysts to exploit confirmation bias to make an optimal portfolio allocation especially during COVID-19 and non-COVID-19 periods. Moreover, the findings of this study might be useful for investors as they help them to make successful investment decision in potential hedging strategies.

First, this is the first scientific work that conducts a stochastic analysis about the impact of emotional biases on the estimated returns and the expectations of optimists and pessimists in cryptocurrency and commodity markets. Second, the originality of this study stems from the fact that the authors make a comparative analysis of hedging behavior across different markets and different periods with and without the impact of confirmation bias. Third, this paper pays attention to the impact of confirmation bias on the expectations and hedging behavior in cryptocurrencies and commodities markets in extremely stressful periods such as the recent COVID-19 pandemic.