A Hybrid Method of Corporate Financial Performance Prediction Based on Common Model and Convolutional Neural Network
Xiaochuan Tian · International Journal of High Speed Electronics and Systems · 2025
Performance data are affected by market environment, business demand, policy changes, and other factors, resulting in an obvious nonlinear relationship between the influencing factors across the period. The convolutional neural network (CNN) method cannot deal with such nonlinear relationship data directly, and the oscillation caused by stochastic gradient descent leads to local optimization, resulting in poor prediction results. Therefore, the interperiod impact prediction method of corporate financial performance based on the Public model is proposed. Based on the enterprise’s financial data, the method involves several steps. First, it extracts the principal component data pertinent to the enterprise’s intellectual capital through principal component analysis. Subsequently, the public model is employed to measure the intellectual capital of the enterprise, utilizing the extracted principal component data related to intellectual capital, such as coefficients and the coefficient of intellectual capital efficiency, among other indicators. Last, the intellectual capital indicators of various enterprises are combined with those of the current enterprise, taking into account the coefficients of the current enterprise’s value-added intellectual capital. Using different enterprise intellectual capital indicators and current enterprise financial performance data as input, the method incorporates machine learning algorithms within a CNN model for iterative feature extraction operations. Additionally, the Adam optimization algorithm is introduced to adaptively adjust the learning rate of the CNN model, thereby enhancing its anti-interference ability. The output of this process is the prediction results detailing the interperiod impact on the enterprise’s financial performance. Experimental results demonstrate that this method can effectively extract the principal components from the enterprise’s financial data and accurately measure the current enterprise’s intellectual capital. Furthermore, it predicts the interperiod impact of the enterprise’s financial performance over the next 12 months, based on factors such as capital utilization efficiency and return on net assets, related to the enterprise’s intellectual capital. The application of this method yields superior results.