A TOE-BP Neural Network Model for Pharmaceutical Digital Transformation Prediction
De Chen · 2025
Scientifically evaluating and predicting the effectiveness of digital transformation is crucial for pharmaceutical enterprises to enhance core competitiveness, optimize resource allocation, and promote industrial upgrading. Based on the Backpropagation (BP) neural network, this study constructs a prediction model for the effectiveness of digital transformation in pharmaceutical enterprises by integrating the TOE framework. Multi-dimensional key factors influencing transformation effectiveness were identified, and 9 core indicators were selected as the model's input layer. The MATLAB software platform was used to train and optimize the model. Empirical results show that the model's maximum prediction error rate is below 5%, demonstrating high prediction accuracy. This research provides an effective new method for quantitatively predicting the effectiveness of digital transformation in pharmaceutical enterprises, contributing to improved scientific rigor and accuracy in forecasting. It offers data support and decision-making references for enterprises in formulating precise digital strategies, evaluating investment returns, and optimizing transformation pathways.