Statistical Methods in Finance 2018

Abstract

Short Term Stock Price Prediction in Indian Market: A Neural Network Perspective

by Soham Banerjee

In the realm of finance, behavior of equity markets have a deep-seated impact on individual investors as well the economy at large. Thus a prescient knowledge of the underlying market dynamics, that orchestrate stock price movements plays a critical role in engineering successful strategies for the investor. A lot of effort has been already devoted on stock price forecasting using traditional time series models (like MA, ARMA, ARIMA, ARCH, GARCH) which model the data using a predefined mathematical framework, restricting their ability to learn latent patterns in the data. In recent times, Artificial Neural Networks(ANN) have garnered a lot of positive attention from researchers in this domain. ANNs are able to consistently outperform traditional models because of their model independent approach which enable them to learn complex hidden patterns in the data using a highly non-linear architecture. In this report we have focused on the application of advanced Neural Network paradigms like stacked Multi Layer Perceptrons(MLP), Long Short Term Memory (LSTM), Gated Recurrent Unit(GRU) and Bidirectional Long Short Term Memory (BLSTM), Gated Bidirectional Recurrent Unit(BGRU) on NSE listed companies to predict short term stock price and compared their performance with a shallow neural network benchmark.

---

---