High-frequency CSI300 futures trading volume predicting through the neural network

Abstract

PurposeFor policymakers and participants of financial markets, predictions of trading volumes of financial indices are important issues. This study aims to address such a prediction problem based on the CSI300 nearby futures by using high-frequency data recorded each minute from the launch date of the futures to roughly two years after constituent stocks of the futures all becoming shortable, a time period witnessing significantly increased trading activities.Design/methodology/approachIn order to answer questions as follows, this study adopts the neural network for modeling the irregular trading volume series of the CSI300 nearby futures: are the research able to utilize the lags of the trading volume series to make predictions; if this is the case, how far can the predictions go and how accurate can the predictions be; can this research use predictive information from trading volumes of the CSI300 spot and first distant futures for improving prediction accuracy and what is the corresponding magnitude; how sophisticated is the model; and how robust are its predictions?FindingsThe results of this study show that a simple neural network model could be constructed with 10 hidden neurons to robustly predict the trading volume of the CSI300 nearby futures using 1–20 min ahead trading volume data. The model leads to the root mean square error of about 955 contracts. Utilizing additional predictive information from trading volumes of the CSI300 spot and first distant futures could further benefit prediction accuracy and the magnitude of improvements is about 1–2%. This benefit is particularly significant when the trading volume of the CSI300 nearby futures is close to be zero. Another benefit, at the cost of the model becoming slightly more sophisticated with more hidden neurons, is that predictions could be generated through 1–30 min ahead trading volume data.Originality/valueThe results of this study could be used for multiple purposes, including designing financial index trading systems and platforms, monitoring systematic financial risks and building financial index price forecasting.

Composite property price index forecasting with neural networks

“…Here, we also consider the scaled conjugate gradient (SCG) (Møller, 1993) and Bayesian regularization (BR) (MacKay, 1992) algorithms. The SCG and BR algorithms, as well as the LM algorithm, have been explored in different varieties of fields (Xu and Zhang, 2021a, 2022a, b, d, h, 2023f, j, p, t, u; Doan and Liong, 2004; Xu and Zhang, 2023n; Kayri, 2016; Khan et al ., 2019; Selvamuthu et al ., 2019). Comparative research of these algorithms can be seen from the literature (Baghirli, 2015; Xu and Zhang, 2022m, 2023a, k, m; Al Bataineh and Kaur, 2018).…”

Office property price index forecasting using neural networks

“…we have taken into consideration the balance between model performance and stabilities in determining the final specification (Xu and Zhang, 2023h). As compared to econometric models, machine learning models might also be subject to increased complexities in terms of model implementations.…”

“…Finally, it is worth noting that similar to econometric models, machine learning models, including NNs, used for forecasting purposes could be subject to the issue of overfitting or underfitting. Thus, in building NN models for forecasts of office property price indices here, we have taken into consideration the balance between model performance and stabilities in determining the final specification (Xu and Zhang, 2023h). As compared to econometric models, machine learning models might also be subject to increased complexities in terms of model implementations.…”

Scrap steel price forecasting with neural networks for east, north, south, central, northeast, and southwest China and at the national level

“…The auto-regressive integrated moving average model (ARIMA), vector auto-regressive model (VAR), and vector error correction model (VECM) are among the most popular and powerful approaches to tackle numerous price forecasting tasks in this area. In recent years, as computing resources and tools are becoming continuously easier and more affordable to reach [100], researchers across the globe have started to show continuously increasing interest in exploring applications of machine learning techniques [101] for the purpose of forecasting commodity prices. Corresponding studies in the literature have covered many different commodities from different economic sectors and industries, including but not limited to those in the agricultural sector, such as soybeans [102][103][104][105][106][107][108], soybean oil [109][110][111], palm oil [112], sugar [113][114][115][116][117][118], corn [102,113,[119][120][121][122][123][124][125][126][127][128][129][130][131], wheat [105,[132][133][134][135][136][137][138]…”

“…The auto-regressive integrated moving average model (ARIMA), vector auto-regressive model (VAR), and vector error correction model (VECM) are among the most popular and powerful approaches to tackle numerous price forecasting tasks in this area. In recent years, as computing resources and tools are becoming continuously easier and more affordable to reach [100], researchers across the globe have started to show continuously increasing interest in exploring applications of machine learning techniques [101] for the purpose of forecasting commodity prices. Corresponding studies in the literature have covered many different commodities from different economic sectors and industries, including but not limited to those in the agricultural sector, such as soybeans [102–108], soybean oil [109–111], palm oil [112], sugar [113–118], corn [102, 113, 119–131], wheat [105, 132–139], coffee [140–146], oats [147], cotton [132, 148], canola [149–151], peanut oil [152–158], green beans [159, 160], and edible oil [112, 153, 161–164], those in the energy sector, such as electricity [165–169], carbon emission allowances [170–174], coal [175–179], crude oil [180–184], heating oil [185–189], and natural gas [190–194], and those in the metal sector, such as lead [195], copper [<...…”