AI-Based Guidance for Strategic Manufacturing Selection to Accelerate Nev Production: a Data-Driven Decision Support Framework

With the quick rise of the New Energy Vehicle
(NEV) industry, there arises a need for effective and sustainable
production practices; yet, current strategy selection techniques
are mostly qualitative in nature. In this research, an artificial
intelligence model is used as a decision-support system to
determine the most appropriate manufacturing strategy for
NEVs. It can be defined as a supervised multi-class classification
problem in which contract manufacturing (CM), skateboard
platform strategy (SPS), and flexible manufacturing system
(FMS) compete. To begin, a dataset of 1000 manufacturing cases
was created based on critical factors related to operations and
sustainability. Various machine learning algorithms, such as
logistic regression, decision trees, random forests, extreme
gradient boosting (XGBoost), and CatBoost, were trained on the
dataset using stratified cross-validation. The results reveal that
CatBoost achieved the highest accuracy (~0.887), whereas
Logistic Regression offered the best balanced approach.