Growing competitiveness and enhancement of automotive industries to adapt to Industry 4.0 has led to the development of many innovative solutions to enhance the quality of production. This can be achieved through efficient use of data generated by various machines involved. Data from various sensors and controllers are stored in Programmable Logic Controllers (PLCs) which can then be retrieved and stored in a centralized storage location like shared drives, private servers or in cloud environments. A machine learning classification model, which is trained using the historic data retrieved from these PLCs, can predict the quality of the final product before it reaches the final stage. With this approach, a part or an assembly can be taken out of the line early, thereby reducing the scrap cost and achieving an improved efficiency of the production. This research provides a consolidated approach that can be used for predictive quality.Growing competitiveness and enhancement of automotive industries to adapt to Industry 4.0 has led to the development of many innovative solutions to enhance the quality of production. This can be achieved through efficient use of data generated by various machines involved. Data from various sensors and controllers are stored in Programmable Logic Controllers (PLCs) which can then be retrieved and stored in a centralized storage location like shared drives, private servers or in cloud environments. A machine learning classification model, which is trained using the historic data retrieved from these PLCs, can predict the quality of the final product before it reaches the final stage. With this approach, a part or an assembly can be taken out of the line early, thereby reducing the scrap cost and achieving an improved efficiency of the production. This research provides a consolidated approach that can be used for predictive quality.