India’s stock market value prediction using deep neural networks

No Thumbnail Available



Journal Title

Journal ISSN

Volume Title


Національний університет «Львівська політехніка»


Master's qualification work was performed by a student of the group KNSSH-21f Deep Shankar Pratap Singh. Theme " India’s Stock Market Value Prediction Using Deep Neural Networks ". The work is aimed at obtaining a master's degree in the specialty 122 "Computer Science". The research was done from February, 2022 till December, 2022. The purpose of the thesis is to build a deep neural network for predicting stock prices of the NIFTY50 index for the Indian stock market and to develop a strategy system to use the built network in investments by investors and researchers. As a result, two neural networks were developed, namely LSTM and GRU. This network architecture was chosen because both are good at capturing the patterns of time-series data, which in our case is stock market data. A total of twenty-four models were created and then compared for their performance. LSTM has been observed to have higher performance than GRU and both models are very good at predicting stock market data.



Recurrent Neural Network (RNN), Artificial Neural Network (ANN), Long Short-term Memory (LSTM), Deep Neural Network (DNN), Gated Recurrent Unit (GRU), Stock Prediction.


Singh D. India’s stock market value prediction using deep neural networks : explanatory note to the master's qualification work : 122 «Computer Science» / Deep Shankar Pratap Singh ; Lviv Polytechnic National University. – Lviv, 2022. – 68 p.