Construction and Optimization of Financial Transformation Decision Model Based on Data Mining

Abstract

Real-time data processing and analysis is crucial in the financial markets since transactions in real time are directly linked to profit. Understanding the integration of finance and business allows the organization to enhance its core competitiveness by improving management and enabling it to lead business expansion more effectively. This manuscript proposes a Sparse Oblique Trees Algorithm (SOTA) optimized with the Waterwheel Plant Algorithm (WWPA) for the construction of financial transformation. The data are collected from multi-national organization dataset. Afterward, the data’s are fed to pre-processing. In pre-processing segment; it removes the noise and enhances the input data’s utilizing Data-Adaptive Gaussian Average Filtering (DAGAF). The outcome from the pre-processing data is transferred to the SOTA. The investment and dividend are successfully classified by using SOTA. The WWPA is used to optimize the weight parameter of SOTA. The proposed SOTA-WWPA is applied in python working platform. The proposed technique was computed by examining performance indicators like precision, F1-score, accuracy, sensitivity and recall. The proposed SOTA-WWPA technique yields improved results in terms of accuracy (16.65%, 18.85%, and 17.89%), sensitivity (16.34, 12.23%, and 18.54%), and precision (14.89%, 16.89%, and 18.23%). The proposed FT-SOTA-WWPA method is contrasted with the existing methods like FT-CNN, FT-MBLSTMNN, and FT-SVM models respectively.