Optimal Portfolio Strategy Research Based on Convolutional Neural Network
- DOI
- 10.2991/978-94-6463-010-7_68How to use a DOI?
- Keywords
- Component; Model; Convolutional Neural Network; Investment Products; Optimal Portfolio Strategy
- Abstract
This paper presents a model for predicting future investment returns using convolutional neural networks. Firstly, the economic indicators at the current time point and the investment return in the same period are considered as vector mode. Secondly, the time series in a continuous period are considered to transform the vector into matrix form to eliminate the influence brought by time fluctuation characteristics. The investment return in the next time is taken as the output value. The convolutional neural network training process is established by using the financial indicators and the time series data of investment return in a period of time to get the predicted value of investment return of the product. The model uses data to predict various investment products and obtains the expected return ratio of the products. It is based on the predicted returns, through the particle swarm optimization algorithm to find the optimal, to achieve the optimal portfolio strategy. Experimental results show that the optimal portfolio strategy based on convolutional neural network proposed in this paper is effective.
- Copyright
- © 2023 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Guangchen Yan PY - 2022 DA - 2022/12/02 TI - Optimal Portfolio Strategy Research Based on Convolutional Neural Network BT - Proceedings of the 2022 International Conference on Artificial Intelligence, Internet and Digital Economy (ICAID 2022) PB - Atlantis Press SP - 664 EP - 670 SN - 2589-4919 UR - https://doi.org/10.2991/978-94-6463-010-7_68 DO - 10.2991/978-94-6463-010-7_68 ID - Yan2022 ER -