Prediction of Stock Price Using XG Boost Integrated Bi-Channel LSTM

Investors' biggest problem is determining the appropriate stock price by studying financial information, which is a difficult process due to enormous and related inefficiencies. So, among the biggest challenges for investors is identifying a stock. Currently, it's very challenging to carry out research in the forecasts for the finance industry, including the stock market, currency value, and stock price. Due to its critical importance in financial consumers' decision-making, the prediction and examination of the stock price is yet another important research subject. A novel Xgboost Integrated Bichannel Long/Short-Term Memory (X-BLSTM) technique is implemented in this article to provide a sophisticated and perfect framework for the share market's price prediction The share value dataset is the first thing we collect to assess the way the suggested X-BLSTM strategy performs. Due to the existence of noisy data, min-max normalization is performed to preprocess the raw dataset. The efficiency of the proposed approach is assessed using several measures, and comparative between the proposed and current methods is also provided. The studies' findings show that the recommended approach outperforms alternative techniques for share value prediction.