Your e-commerce company deployed a product recommendation system six months ago. The system uses a machine learning model trained using historical sales data from the previous year. The model performed well initially. When customers were shown product recommendations, the average sale value increased by 14 percent. In the past month, the model has generated an average increase of only 2 percent. The model has not changed since it was deployed six months ago. What could be the cause of the decrease in effectiveness, and what would you recommend to correct it?