An innovative method for highly accurate stock price forecasting: a case study on HSI

Volatility in the stock market is attributable to many interrelated factors operating in the background. Changes in the unemployment rate, global economic data, immigration policies, public health conditions and monetary policies that impact nations are all potential causes. All participants pursue a comprehensive stock market assessment to increase profits and decrease risks. The globe is searching for a precise and trustworthy forecasting model encompassing the highly variable and nonlinear market behaviour inside a comprehensive framework. This study predicts the close price of the Hang Seng Index (HSI) the following day using a hybrid model called Long Short-Term Memory (LSTM) with a combination of the artificial bee colony. The proposed model achieved optimal outcomes by utilising conventional factors, including a Root Mean Square Error (RMSE) of 180.21, a Mean Squared Error (MSE) of 32474, a coefficient of determination of 0.9941 and a Mean Absolute Error (MAE) of 135.61.