Data-Driven Marketing for Promoting AI-Enhanced Vehicle Safety Features
Abstract
This research aims at developing a data driven marketing communication plan on AI proper utilization for offering vehicle safety features with major emphases on normalization, embedded feature selection and neural networks. First, the identified challenge responds to the problem of analyzing consumer information and improving the marketing strategy in car-related industries that produce significant amounts of data. Normalization methods allow to scale different data sets in the same way, thus improving model performances and decreasing variability. The obvious techniques of the feature selection which include LASSO regression and the scoring of the feature importance from gradient-based boosting models are integrated in the analysis to keep it concise by suggesting that only important predictors should be accounted for, thereby reducing computational expense. Neural networks are used due to their performance in Non-linear mapping and interaction identification in big data for predicting the consumer profile and market trends.