Author:
Liu Chang,Shan Huilin,Tian Zhihao,Cheng Hangyu
Abstract
This article aims to develop a quantitative trading strategy that maximizes profits while finding the best balance of risk and return. We built a high-frequency trading strategy model to maximize profits. We first used the Apriori algorithm to find frequency item sets in historical data before fitting the best daily dynamic position adjustment functions for gold and bitcoin using mathematical statistics and other methods based on price movements. Then we can trade to increase and decrease positions in gold and bitcoin based on the positions suggested by the dynamic position adjustment function. We also simulated three investors with different risk preferences trading using this high-frequency trading model for up to five years and obtained return of 266.05 %, 152.51 %, and 33.29 %, respectively.
Reference10 articles.
1. Duffee G R. Stock returns and volatility a firm-level analysis[J]. Journal of financial Economics, 1995, 37(3): 399-420.
2. Argiddi R V, Apte S S. Future trend prediction of Indian IT stock market using association rule mining of transaction data[J]. International Journal of Computer Applications, 2012, 39(10): 30-34.
3. Moghar A, Hamiche M. Stock market prediction using LSTM recurrent neural network[J]. Procedia Computer Science, 2020, 170: 1168-1173.
4. Shuang Sun. Apriori association rules for analyzing financial data [J]. National Distribution Economy,2019(02):109-110.
5. Xiudong Wang, Yingchun Hu, Hui Li. A study on the application of improved Apriori algorithm in stock analysis [J] Science and Technology Bulletin,2013,29(03):125-128.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献