Analysis and Prediction for IT Sector Growth Using Deep Learning Approaches

Abstract

Data mining involves extracting valuable insights, patterns, correlations, and trends from large datasets stored in database repositories. Machine learning and data mining approaches are used to analyse and predict various research areas with the help of statistical, mathematical, and computational modelling and techniques. This paper considers the information technology sector dataset for analysis and prediction using machine learning, and deep learning approaches. It is used to find future predictions based on four different parameters: open, high, low, and close, using familiar machine learning approaches, proposed stochastic model, and deep learning approaches like linear regression, multilayer perceptron, M5P, random forest, random tree, REP tree, proposed deep learning approaches called Gated Recurrent Units with Interior Point Optimization Technique (GRU-IPOT). Based on various results and discussions, deep learning approaches return the best results compared to machine learning approaches. Numerical illustrations are provided to prove the proposed results with test statistics or accuracy parameters.