This WSJ article gives examples when ML-based solutions have been enhanced by the inclusion of pre-defined domain-specific models. “Machine learning is a statistical modeling technique, which finds and correlates patterns between inputs and outputs without necessarily capturing their cause-and-effect relationships. Data derived from human behavior is dynamic and ever-changing. Such messy data is difficult to analyze to make predictions.” Link Advantages and the integrated models:

• they can be trained or customized with much smaller data sets
• they can tolerate much more noise in the data
• they can be continually updated with new data reflecting changing conditions
• it’s easier to explain how a decision or recommendation was arrived at
• such augmented AI solutions help capture cause-and-effect relationships.