Levy Flight Strategy with Tasmanian Devil’s Optimization for Financial Market Forecasting and Investment Decision

Decision-making in the stock market is complex, demanding substantial trading experience and expertise. However, this process does not eliminate boundaries but rather highlights their fluid and interconnected nature. This paper, Levy Flight Strategy with Tasmanian Devil’s Optimization (LTDO) for feature selection and Convolutional Neural Network (CNN) for classification for highly efficiently at detecting patterns in data, which is crucial in financial forecasting as patterns in historical data. Initially stage is pre-processing is considering the min max is performed to handle less sensitive and non-uniform values. The LTDO is efficiently in feature selection, which helps to reduce the dimensionality of input data, ensuring that only the most relevant feature is used for forecasting. The CNN are particularly useful for analysing historical financial data and capability of feature further enhances the model predictive performance. The proposed ensemble model technique for ship motion detection is achieving better outcomes such as high accuracy of 92.81%, precision of 90.13%, recall of 90.59% and F1 score of 90.95% respectively. The existing technique such Random Forest (RF) and Long Short-Term Memory (LSTM) are evaluated of proposed method.