System and method for predicting process changes by using key factors in commercial chemical process

A system for predicting process changes by using key factors in a commercial chemical process, the system comprising:

• a key factor extraction and individual tag importance backup unit that extracts yield key factors by calculating the importance of each tag, and backs up importance data for each tag;
• and
• a yield prediction model training and yield prediction performing unit that performs yield prediction model training by using the importance of each tag accumulated in the key factor extraction and individual tag importance backup unit, and performs yield prediction so as to output a yield prediction result, evaluates performance, and selects an optimal prediction model,
• wherein the yield prediction model training and yield prediction performing unit is further configured to designate the optimal prediction model as a champion model, iteratively retrain a challenge model using the importance of each tag accumulated in the key factor extraction and individual tag importance backup unit together with newly accumulated process data on a set schedule, evaluate the challenge model against the champion model, generate the yield prediction result as a weighted ensemble of the champion model and the challenge model, and replace the champion model with the challenge model upon the challenge model achieving a lower prediction error than the champion model, and
• wherein the key factor extraction and individual tag importance backup unit and the yield prediction model training and yield prediction performing unit are each implemented via at least one processor.