Unveiling Transformative Insights via Cross-Modal Learning and Natural Language Processing for Enhanced Supply Chain Intelligence

Abstract

This day's quickly developing business landscape, supply chains have become more globalized, intricate, and multi-covering, making them crucial for companies to navigate through disruptions and unpredictability. The major which are addressed in the supply chain process are lack of transparency and visibility of the supply chain network and that's leads to delay and inefficiency in the process. In order to overcome those drawbacks in the supply chain process, in this article an enhanced supply chain intelligence is developed which performs Unveiling Transformative Insights using the learning process like Cross-Modal Learning (CML) and Natural Language Processing (NLP). The implementation of these techniques is carried out in the software Python. This analysis consists of certain calculation called enhanced supply chain analysis, sales revenue Vs SKU analysis, various modes cost analysis, Lead time vs different supplier and location. The comparative analysis is performed among the technique like RF regression, SARIMA-LSTM-BP and BiLSTM model. The parameters which are involved in this performance analysis are MAE, MSE, RMSE and R^2.