Forecasting of Service Sectors in Indian Markets Using Machine Intelligence

EasyChair Preprint no. 8700

Abstract

The study examines stock index closing from myriad set of technical and fundamental analysis variables extracted from real market data to assist forecast of market closing. For this, major service sector indices of Bombay stock exchange (BSE) and National stock exchange (NSE) with historical data from 2004-2016 were taken from banking industry. The predictive performance for index closing phenomena using automatic linear modeling, time-series based econometric forecasting, vector auto regression and artificial neural network based models were compared. Results indicate that BSE had higher forecast accuracy with autoregressive models and was affected more by market volatility. On the other hand, NSE was impacted by quarterly performance that can be modeled using neural networks. These variant effects were contrasted with latest state-of-art research to identify the challenges of developing advanced intelligent market forecast systems.

Keyphrases: Artificial Neural Networks, hybrid models, Stock index forecasting, Vector Autoregression

@Booklet{EasyChair:8700,
  author = {R Arjun and K. R Suprabha},
  title = {Forecasting of Service Sectors in Indian Markets Using Machine Intelligence},
  howpublished = {EasyChair Preprint no. 8700},

  year = {EasyChair, 2022}}