Quantitative Investment Based on Artificial Neural Network Algorithm
International Journal of u- and e- Service, Science and Technology
Financial investment has become an important issue, there are many trading strategies and parameters based on quantitative models, this paper use neural network algorithm to optimization strategy parameters, various combinations of optimization strategies, as well as the evolution of new strategies to generate better returns. The empirical results show that this method has a stable and substantial return on investment, neural network can be used as an aid for decision making investments in
... ities. Artificial neural network is a new high-tech research area Since 1980s, involving a variety of disciplines, attracting many neurophysiologists, psychologists, mathematician, computer and information scientists, engineers to research and apply. Artificial neural network has entered the stage of steady development, its features and advantages, mainly in three aspects: a self-learning function, associative memory function, with the ability to find the optimal solution for high-speed. Neural network model mainly consider the network topology connection characteristics of neurons, learning rules. Currently, nearly 40 kinds of neural network model, widely used in the field of artificial neural network, including pattern recognition, signal processing, knowledge engineering, expert systems, optimize the combination of robot control. In 1990, Specht based on radial basis function neural network and Parzen window function density estimation method based on the proposed A new artificial neural networksprobabilistic neural network (Probabilistic Neural Network, PNN), which utilizes Priori probability-Bayes optimal law of the sample and determine the principles for a new classification of samples, but also from multivariate normal points Restrictions cloth and other conditions, and in the course of operation can be calculated PNN posterior probability of a new input sample is classified, so Provide explanations for the results. PNN its simple structure, fast training process and good ability to promote superior Potential performance has been widely used in many fields, such as stock forecasts. PNN has to be applied in face recognition, credit evaluation, quality assessment, remote sensing image classification, forecasting river bed morphology and sensor fault diagnosis and other fields. In this paper, the radial basis function -probabilistic neural network model is explored. Then the accuracy and performance of the predictions are studied with comparisons. Output layer (also called competitive layer): get M nodes as input by the summation layer output layer, and then get the output in accordance with the model output layer, the network final output is J class.