Dự báo khối lượng giao dịch giao sau CSI300 tần suất cao thông qua mạng thần kinh

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Xiaojie Xu, Yun Zhang

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Tạp chí Kinh tế và Ngân hàng châu Á, 2024

Mô tả vật lý: tr.27-49

Bộ sưu tập: Báo, Tạp chí

ID: 458199

Thêm vào giỏ Liên kết toàn văn

Mục đích – Đối với các nhà hoạch định chính sách và người tham gia thị trường tài chính, việc dự đoán khối lượng giao dịch của các chỉ số tài chính là vấn đề quan trọng. Nghiên cứu này nhằm mục đích giải quyết vấn đề dự đoán như vậy dựa trên hợp đồng tương lai gần CSI300 bằng cách sử dụng dữ liệu tần suất cao được ghi lại mỗi phút kể từ ngày ra mắt hợp đồng tương lai cho đến khoảng hai năm sau khi các cổ phiếu cấu thành của hợp đồng tương lai đều có thể bán khống, một khoảng thời gian chứng kiến các hoạt động mua bán tăng lên đáng kể.Thiết kế/phương pháp/cách tiếp cận – Để trả lời các câu hỏi sau đây, nghiên cứu này sử dụng mạng lưới thần kinh để mô hình hóa chuỗi khối lượng giao dịch không đều của hợp đồng tương lai lân cận CSI300: nghiên cứu có thể sử dụng độ trễ của chuỗi khối lượng giao dịch để đưa ra dự đoán hay không
nếu đúng như vậy, những dự đoán có thể đi xa đến đâu và những dự đoán đó có thể chính xác đến mức nào
liệu nghiên cứu này có thể sử dụng thông tin dự đoán từ khối lượng giao dịch của CSI300 và hợp đồng tương lai xa đầu tiên để cải thiện độ chính xác của dự đoán và cường độ tương ứng là bao nhiêu
mô hình phức tạp đến mức nào
và những dự đoán của nó chắc chắn đến mức nào?Những phát hiện mới – Kết quả của nghiên cứu này cho thấy rằng một mô hình mạng nơ-ron đơn giản có thể được xây dựng với 10 nơ-ron ẩn để dự đoán chính xác khối lượng giao dịch của hợp đồng tương lai gần CSI300 bằng cách sử dụng dữ liệu khối lượng giao dịch trước 1–20 phút. Mô hình dẫn đến sai số bình phương trung bình gốc khoảng 955 hợp đồng. Việc sử dụng thông tin dự đoán bổ sung từ khối lượng giao dịch của hợp đồng CSI300 và hợp đồng tương lai xa đầu tiên có thể mang lại lợi ích hơn nữa cho độ chính xác của dự đoán và mức độ cải thiện là khoảng 1–2%. Lợi ích này đặc biệt quan trọng khi khối lượng giao dịch của hợp đồng tương lai gần CSI300 gần bằng 0. Một lợi ích khác, mặc dù sẽ làm mô hình trở nên phức tạp hơn một chút với nhiều nơ-ron ẩn hơn, đó là các dự đoán có thể được tạo ra thông qua dữ liệu khối lượng giao dịch trước 1–30 phút.Tính mới/giá trị nguyên bản – Kết quả của nghiên cứu này có thể được sử dụng cho nhiều mục đích, bao gồm thiết kế hệ thống và nền tảng giao dịch chỉ số tài chính, giám sát rủi ro tài chính có hệ thống và xây dựng dự báo giá chỉ số tài chính.Purpose – For 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/approach – In 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?Findings – The 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/value – The 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.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR