In this study, we attempt to predict global agricultural commodity futures prices through analysis of multivariate time series. Our motivation is based on the notion that datasets of agricultural commodity futures prices involves a mixture of long- and short-term information, linear and non-linear structure, for which traditional approaches such as Auto-Regressive Integrated Moving Average (ARIMA) and Vector Auto-Regression (VAR) may fail. To tackle this issue, Long- and Short-Term Time-series Network (LSTNet) is applied for prediction. Empirical results show that LSTNet achieves better performance over that of several state-of-the-art baseline methods on average and in most periods based on three performance evaluation measures and two tests of performance difference.
In this study, we attempt to discover and predict stock index patterns through analysis of multivariate time series. Our motivation is based on the notion that financial planning guided by pattern discovery and prediction of stock index prices maybe more realistic and effective than traditional approaches, such as Autoregressive Integrated Moving Average (ARIMA) model. A three-stage architecture constructed by combining Toeplitz Inverse Covariance-Based Clustering (TICC), Temporal Pattern Attention and Long-Short-Term Memory (TPA-LSTM) and Multivariate LSTM-FCNs (MLSTM-FCN and MALSTM-FCN) is applied for pattern discovery and prediction of stock index. In the first stage, we use TICC to discover repeated patterns of stock index. Then, in the second stage, TPA-LSTM that considers weak periodic patterns and long short-term information is used to predict multivariate stock indices. Finally, in the third stage, MALSTM-FCN is applied to predict stock index price pattern. The Hangseng Stock Index and eleven industrial sub-indices are used in the experiment. Empirical results show that the three-stage architecture achieves satisfactory and better performance than traditional methods, such as Naive Bayes Classifier (NB), Support Vector Machine Classifier (SVM), Random Forest (RF), etc. Moreover, we construct equal proportion portfolios based on the bullish trading rules to further analyze the feasibility of the proposed three-stage architecture. Seven comprehensive stock indices are used in the experiment. Empirical results show that the portfolio based on the proposed three-stage architecture presents better performance than the market-based portfolio. These findings may provide new direction for the portfolio construction and risk aversion.
Carbon price prediction is of great importance to regulators and participants in the carbon trading market. It is the basis for developing policies related to the carbon trading market and stabilizing that market. Considering the numerous factors that influence carbon prices in China, dimensionality reduction is needed to improve the prediction accuracy and efficiency. However, the traditional dimensionality reduction methods fail to fully consider the role of influencing factors, which has certain limitations. In this paper, a new dimensionality reduction method, namely scaled principal component analysis (s-PCA), is employed to improve the prediction accuracy of carbon prices. Firstly, a factor library that influence carbon prices is constructed from three perspectives: technical indicators, financial indicators and commodities indicators. Then, the s-PCA method is used to reduce the dimensionality of factors influencing carbon price. Next, two different methods are used to predict carbon prices, including traditional regression method and Long Short-Term Memory (LSTM) method. Finally, the economic value of the s-PCA method is examined by constructing investment portfolios. The empirical results of the Hubei Emissions Exchange show that the s-PCA model outperforms other competing models both in- and out-of-sample. In addition, the LSTM model could improve the performance of the s-PCA model in carbon price prediction. From a market timing perspective, investors can achieve a greater return and a larger Sharpe ratio using the s-PCA method than using other comparative methods and buy-and-hold strategy. Therefore, the s-PCA method is effective and robust in predicting carbon price.
In this study, we propose a predictive model TabLSTM that combines machine learning methods such as TabNet and Long Short-Term Memory Neural Network (LSTM) with a complete factor library for stock index trend prediction. Our motivation is based on the notion that there are numerous interrelated factors in the stock market, and the factors that affect each stock are different. Therefore, a complete factor library and an efficient feature selection technique are necessary to predict stock index. In this paper, we first build a factor database that includes macro, micro and technical indicators. Successively, we calculate the factor importance through TabNet and rank them. Based on a prespecified threshold, the optimal factors set will include only the highest-ranked factors. Finally, using the optimal factors set as input information, LSTM is employed to predict the future trend of 4 stock indices. Empirical validation of the model shows that the combination of TabNet for factors selection and LSTM outperforms existing methods. Moreover, constructing a factor database is necessary for stock index prediction. The application of our method does not only show the feasibility to predict stock indices across different financial markets, yet it also provides an complete factor database and a comprehensive architecture for stock index trend prediction, which may provide some references for stock forecasting and quantitative investments.
This study attempts to predict stock index prices using multivariate time series analysis. The study’s motivation is based on the notion that datasets of stock index prices involve weak periodic patterns, long-term and short-term information, for which traditional approaches and current neural networks such as Autoregressive models and Support Vector Machine (SVM) may fail. This study applied Temporal Pattern Attention and Long-Short-Term Memory (TPA-LSTM) for prediction to overcome the issue. The results show that stock index prices prediction through the TPA-LSTM algorithm could achieve better prediction performance over traditional deep neural networks, such as recurrent neural network (RNN), convolutional neural network (CNN), and long and short-term time series network (LSTNet).