• P. Akhila
• Dr.P.Krishna Subba Rao
• CH.Avinash

Predictive analytics has been developed in significance along with the emergence of big data. In the past few decades, forecasting of stock market is gaining more attention as the profitability of investors in the stock market mainly depends on the predictability. To predict the stock prices there are many algorithms used. Recurrent neural nets are a specific type of ANNs (artificial neural networks) aimed to recognize patterns in sequences of data, such as text, genomes, handwriting, the spoken word, or time series data originating from sensors, stock markets and government agencies. Many recent works on Google stock prediction are implemented using GRU (Gated recurrent units). The limitation of the existing work using GRU is it has a high loss rate. So, for efficiency and accuracy, our proposed method uses LSTM (long short-term memory). LSTMs help conserve the error that can be back propagated through time and layers. By maintaining a more constant error, they allow recurrent nets to continue to learn over many time steps. The efficiency of the proposed method is proved by comparing the performance of it with the previous method using GRU.

Predictive analysis, big data, recurrent neural nets, ANN, genomes, GRU, LSTM

"STOCK MARKET PREDICTION USING LSTM NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 5, page no.582-592, May-2018, Available :http://www.jetir.org/papers/JETIR1805518.pdf

"STOCK MARKET PREDICTION USING LSTM NEURAL NETWORKS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 5, page no. pp582-592, May-2018, Available at : http://www.jetir.org/papers/JETIR1805518.pdf