Predicting new and existing product sales in semiconductors using Amazon Forecast

This is an exciting example from NXP of how machine learning (ML) can enhance and support the work of product managers and Line of Business decision-makers. NXP was interested in predicting the product lifecycle (Introduction, Growth, Maturity, and Decline) of newly introduced products. This enables to further allocate R&D funding to the products generating the highest amounts of sales or products with the highest potential to maximize the ROI for R&D activity. Additionally, NXP can predict long-term sales on a micro level, which gives them a bottom-up look at how their revenue changes over time.

On the ML side, the blog discusses novel method developed to predict the product lifecycle while taking into consideration a cold start. It introduces a point cloud-based method and also discusses the introduction of additional features, including product description as a bag of words to tackle the cold start problem for predicting the product lifecycle curve.

“… [the] Amazon Machine Learning Solutions Lab … delivered a sales forecast model, which complements our current way of manual forecasting, and helped us model the product lifecycle with novel machine learning approaches using Amazon Forecast and Amazon #SageMaker.” Bart Zeeman.