NNAR AS A RELIABLE TOOL FOR PREDICTING VOLUME-WEIGHTED AVERAGE PRICE BEHAVIOUR

Abstract

In this competitive era of financial expertise predicting stock behavior has become significant because it facilitates data-driven decisions that help traders design their investment strategy which impacts their portfolios. This research aims to use Neural Network Auto-regressive models to analyze Volume- weighted average prices and make predictions. By examining data and interrelated financial variables the project aims to provide forecasts that reveal trends and risks involved in investment decisions. Utilizing NNAR models will help the understanding of the future ahead of us which gives insights in decision-making. This study not only contributes to the field of analytics but also has practical applications that contribute to investment strategies, risk management, and policy development. The NNAR model is an integration of a feedforward neural network with lagged inputs and a single hidden layer with non-linear functions it is said to be one of the best tools for analyzing time-series data.