Stock price crashes have occurred frequently in the Chinese security market during the last three decades. They have not only caused substantial economic losses to market investors but also seriously threatened the stability and financial safety of the security market. To protect against the price crash risk of individual stocks, a prediction and explanation approach has been proposed by combining eXtreme Gradient Boosting (XGBoost), the Non-dominated Sorting Genetic Algorithm II (NSGA-II), and SHapley Additive exPlanations (SHAP). We assume that financial indicators can be adopted for stock crash risk prediction, and they are utilized as prediction variables. In the proposed method, XGBoost is used to classify the stock crash and non-crash samples, while NSGA-II is employed to optimize the hyperparameters of XGBoost. To obtain the essential features for stock crash prediction, the importance of each financial indicator is calculated, and the outputs of the prediction model are explained by SHAP. Compared with the results of benchmarks using traditional machine learning methods, we found that the proposed method performed best in terms of both prediction accuracy and efficiency. Especially for the small market capitalization samples, the accuracy of classifying all samples reached 78.41%, and the accuracy of identifying the crash samples was up to 81.31%. In summary, the performance of the proposed method demonstrates that it could be employed as a valuable reference for market regulators engaged in the Chinese security market.
Futures price-movement-direction forecasting has always been a significant and challenging subject in the financial market. In this paper, we propose a combination approach that integrates the XGBoost (eXtreme Gradient Boosting), SMOTE (Synthetic Minority Oversampling Technique), and NSGA-II (Non-dominated Sorting Genetic Algorithm-II) methods. We applied the proposed approach on the direction prediction and simulation trading of rebar futures, which are traded on the Shanghai Futures Exchange. Firstly, the minority classes of the high-frequency rebar futures price change magnitudes are oversampled using the SMOTE algorithm to overcome the imbalance problem of the class data. Then, XGBoost is adopted to construct a multiclassification model for the price-movement-direction prediction. Next, the proposed approach employs NSGA-II to optimize the parameters of the pre-designed trading rule for trading simulation. Finally, the price-movement direction is predicted, and we conducted the high-frequency trading based on the optimized XGBoost model and the trading rule, with the classification and trading performances empirically evaluated by four metrics over four testing periods. Meanwhile, the LIME (Local Interpretable Model-agnostic Explanations) is applied as a model explanation approach to quantify the prediction contributions of features to the forecasting samples. From the experimental results, we found that the proposed approach performed best in terms of direction prediction accuracy, profitability, and return–risk ratio. The proposed approach could be beneficial for decision-making of the rebar traders and related companies engaged in rebar futures trading.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.