A Survey on different datasets employed during stock market prediction

Main Article Content

Shobhita Singh, Dr. DivyaKhanna

Abstract

Stock market prediction is a complex yet an essential task for the investors to earn profits. It is complicated to determine the relation between the input and the output because of its randomness and volatility. Applying the available past and present data and information, one can forecast the stock market cost. Therefore, the historical market datasets play a vital role in the prediction by notifying about technical indicators like daily prices, volume traded information surrounding various stocks, closing price, opening price, highest and lowest intraday price, various fundamental ratios (like PE ratio, liquidity ratio, solvency ratio, activity ratio etc.), last traded price etc. There are several datasets that are been employed in various research papers used for the prediction of numerous stocks price. The most often used datasets for machine learning are the NSE, Chinese stock exchange, S&P 500, NYSE, NASDAQ, Istanbul stock exchange national 100 index, standard & poor's 500 return index, and the stock market return index of Germany. The suggested study's goal is to conduct a review of different datasets used in recent research publications over the last five years in order to help forthcoming researchers keep up with the current developments in the area of datasets for stock market prediction using any approach (machine learning or deep learning).

Article Details

Section
Articles