Machine Learning for Root Cause Analysis – Applications for Supply Chain Planning – NXP
|Company Name / Department||NXP|
Ana Glaser (US), Pavle Kecman (NL)
|Housing arranged by company||No|
The world leader in secure connectivity solutions for embedded applications, NXP is driving innovation in the secure connected vehicle, end-to-end security and IOT smart connected solutions markets.
As the world’s 5th largest chipmaker, the company has 29,000 employees in over 30 countries, with approximately $13B in annual revenue.
The supply chain linear programming engine considers supply, demand, capacity and other data elements to deliver over 1,500 supply plans on a weekly basis, calculating an expected revenue composed of “capacity feasible sales”
Every week, several product families see a significant reduction on the expected feasible sales revenue.
The purpose of this project is to identify the best approach to determine what caused the unexpected variation in the weekly supply plan.
Goals of the Project
As part of this project we would like to explore various techniques (such as conventional ML, explainable AI and causal inference) to identify the root cause in a complex system and assess its effectiveness against our sample data.
This project consists of three phases:
- Understand the supply chain planning and engine output data available for modeling.
- Propose feature engineering and data preparation required to conduct the experiments.
- Develop a prototype model to demonstrate and assess the effectiveness of the proposed solution.
Essential Student Knowledge
Python, Machine Learning methodologies.
More information: firstname.lastname@example.org