Stock Market Investment Suggestion using Deep learning

The task of forecasting the outcome of a stock market has traditionally posed a challenge for professionals in the fields of statistics and finance. The primary justification for this projection is the strategy of investing in stocks that are anticipated to appreciate and simultaneously divesting those that are anticipated to depreciate. When attempting to forecast subsequent years’ prices for shares and the trajectory of the stock market, typically one of two methodologies is employed. The initial type of examination is referred to as “vital assessment,” which involves utilizing a company’s methodology and fundamental data such as market standing, expenses, and annualized growth rates to make inferences. The latter pertains to a profound examination that involves scrutinizing historical share prices alongside estimates to forecast the future of the company. This study examines historical graphs and developments to predict the future movements in the market. The present article offers a thorough exposition of the actualization of our strategy for foreseeing the stock market’s movements. The methodology employs K-nearest-neighbor clustering, in tandem with Long Short-Term Memory and Decision Making, to operationalize the investment recommendation. The efficacy of the strategy has been successfully confirmed via a sequence of experiments that yielded satisfactory results.