ABSTRACT
Quantitative investment refers to securities trading strictly guided by computer algorithms. With the advancements in big data technology, quantitative investment has gained increasing significance in the global financial trading market. However, the current market information is complex, and product prices are influenced by various factors, making it challenging to extract effective indicators from the vast amount of market data and formulate trading strategies. To address this issue, this study proposes a forecasting model for quantitative investment based on BP neural networks and time series analysis, resulting in improved forecasting accuracy. The paper adopts the median to substitute indicators during the relevant time, homogenizing the time interval. The chosen BP neural network prediction model exhibits robust nonlinear mapping capabilities and fault tolerance. The model undergoes testing, yielding MAE and MAPE test results primarily at 0.08 and 0.03, respectively. The predicted values demonstrate a high degree of alignment with real values, showcasing an effective prediction outcome.
- Khodadadi A, Tütüncü R H, Zangari P J. Optimisation and quantitative investment management[J]. Journal of Asset Management, 2006, 7: 83-92.Google ScholarCross Ref
- Zhao Yang. Domestic quantitative market still in rapid development stage[N]. Financial Times,2023-07-28(007).Google Scholar
- Li Cong. Research on quantitative investment strategy based on LSTM neural network stock price prediction[D]. Yunnan University of Finance and Economics,2022.Google Scholar
- Zhu Rui. Research on stock index price prediction and quantitative investment strategy based on LSTM neural network[D]. Yunnan University of Finance and Economics,2023.Google Scholar
- Zhu Han. AI further penetrates private equity strategies by empowering computerized investment[N]. China Securities Journal, 2023-08-14(J07).Google Scholar
- FENG Yongchang, ZHANG Jianmin, LIU Tianquan. Introduction and legal analysis of classic cases of foreign quantitative investment[J]. Tsinghua Financial Review,2016(02):45-48.Google Scholar
- Khemraj T, Yu S. The effectiveness of quantitative easing: new evidence on private investment[J]. Applied Economics, 2016, 48(28): 2625-2635.Google ScholarCross Ref
- Fan X, Li H, Zhu Z. A quantitative investment model based on multi-fractal theory and support vector machine[C]//2014 International Conference on Computing, Management and Telecommunications (ComManTel). IEEE, 2014: 239-244.Google Scholar
- Su Ziqiu. Research on quantitative investment strategy based on artificial intelligence technology [D]. Guilin University of Electronic Science and Technology,2023.Google Scholar
- Jin Ye. Research on quantitative trading strategies and risks in financial markets[J]. Financial Economy,2019(16):124-125.Google Scholar
- Hao Chen. Research on market effect and premium of corporate governance[M]. Science Press,2016.Google Scholar
- Wang Bing,Li Xiang. The Development of Quantitative Investment in Domestic Market[J]. Economic Perspectives(Next),2011(03):46-47.Google Scholar
- Fang Y, Chen J, Xue Z. Research on quantitative investment strategies based on deep learning[J]. Algorithms, 2019, 12(2): 35.Google ScholarCross Ref
- Zhang Wenjuan. The development of quantitative investment in domestic market[J]. China Business Journal,2020(16):16-17.Google Scholar
- Chen Lili. Research on quantitative analysis of stocks based on BP neural network [D]. Zhejiang University of Technology,2018.Google Scholar
Recommendations
Hybridization of Artificial Neural Network and Particle Swarm Optimization Methods for Time Series Forecasting
Recently, Particle Swarm Optimization PSO has evolved as a promising alternative to the standard backpropagation BP algorithm for training Artificial Neural Networks ANNs. PSO is advantageous due to its high search power, fast convergence rate and ...
Comparative analysis of time-series forecasting algorithms for stock price prediction
AISS '19: Proceedings of the 1st International Conference on Advanced Information Science and SystemThis paper predicts the average stock price for five datasets by utilizing the historical stock price data ranging from April 2009 to February 2019. Autoregressive Integrated Moving Average (ARIMA) model is used to generate the baseline, while Long ...
Time series forecasting by recurrent product unit neural networks
Time series forecasting (TSF) consists on estimating models to predict future values based on previously observed values of time series, and it can be applied to solve many real-world problems. TSF has been traditionally tackled by considering ...
Comments