Prediction Method Based On LSTM Algorithm

Forecasting stock market prices have always been challenging task for many business analyst and researchers.In fact,stock market price prediction is an interesting area of research for investors.For successful investment,many investors are interested in knowing about the future situation of the market.Effective prediction systems indirectly help traders by providing supportive information such as the future market direction.Data mining techniques are effective for forecasting future by applying various algorithms to data.Many researchers have contributed in this area of chaotic forecast in their ways.Since many year different method have been used for resolving many problem in this way.In this project,we study the problem of stock market forecasting using Recurrent Neural Network(RNN)with Long Short-Term Memory(LSTM).The purpose of this project is to examine the feasibility and performance of LSTM in stock market forecasting.We test the performance of the LSTM with other types of algorithm.The Neural Network is trained on the stock quotes using the Back propagation Algorithm which is used to predict share market closing price.In our work we use different inputs to build our recurrent neural network to see what the impact on the different predictions value.The Accuracy of the performance of the neural network is compared with other accuracy of different method.We also prove that some algorithm are good for prediction in a short period but not as a long time.In our work of prediction prices,we got the data on the site of kaggle.comDuring our work we use three different type of technique.The different types of technique are:the first technique used to calculate the loss error is named The technique of standard Average and the linear regression news.;the second we use is called the technique of Exponential Moving Average,and finally we use the last technique we use is called the long Short Term memory Network or also called(LSTM).After using these different methods we prove that the long short Term Memory Network is the best Method for prediction series network.