Leading Indicators using Fuzzy Joins – NXP

 Overview

Company Description

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 chip-maker, the company has 29,000 employees in over 30 countries, with approximately $9B in annual revenue.

Project Description

In the demand management organization we do not leverage Design Registrations / Design Wins as predictors because it is complex for us to align to the data directly, since some of the part numbers registered may end up changing just enough to prevent us from linking them back to our sales data.

As part of this project we would like to explore the concept of fuzzy joins, understand how they are used in a business sense and how they are applied to forecasting in the semiconductor industry.

Goals of the Project

Leverage engineering design wins as leading indicators for future revenue.

Deliverables

This project consists of three phases:

1) Define the technique and research how this technology is used in a typical business setting.

2) Explain how this technology is leveraged for forecasting in the semiconductor industry.

3) Develop a prototype demonstrating this capability by aligning our engineering design registrations and design wins to our revenue data, enabling better forecasts by using this as a leading indicator.

Essential Student Knowledge

Database structures, machine learning methodologies, basic SQL.

More information: escf@tue.nl