Deep Learning For Multivariate Financial Time Series

Deep learning is a framework for training and modelling neural networks which recently have surpassed all conventional methods in many learning tasks,prominently image and voice recognition.Since the early 1980s,the artificial neural network technology has been developing rapidly around the whole world,it was the mathematical model that is established on the basis of the simulation of the human brain structure and thinking.It also can solve many problems such as image recognition,speech recognition,natural language processing,which have caused the high attention of scholars in the domestic and abroad.2006Hinton and others proposed the concept of deep learning on the base of artificial neural network.Deep learning is the neural network of the depth that contains a lot of hidden layer.lt has more excellent ability about characteristics of learning and can abstract and expression data more essential Deep learning optimize the training process of the data model by initializing data one by one,and then improve the accuracy of the model prediction classification.In the past two years,the use of deep learning methods to deal with the high-frequency financial data sets off a wave of the rise of research and application.This thesis uses deep learning algorithms to forecast financial data.The deep learning framework is used to train a neural network.The deep neural network is a DBN coupled to a MLP.he results obtained from the deep neural network are compared to benchmarks from a logistic regression network,a multilayer perceptron and a naive benchmark.The results obtained from the deep neural network are better and more stable than the benchmarks.The findings support that deep learning methods will find their way in finance due to their reliability and good performance.