Designing a Concept for Long-Horizon Visibility in Large Project Supply Chains

 Overview

Company Description 

Hilti stands for innovation and direct customer relationships. More than 34,000 employees around the world, in over 120 countries, contribute to making our customers’ work more productive, safer and more sustainable. We do this with our hardware, software and service offering. With roughly 300,000 customer contacts each day, many ideas come directly from our customers. If there is a challenge for which no Hilti solution exists, one will be developed. This is why we invest approximately 7 percent of sales each year in research and development. From product development to manufacturing, logistics, sales and services, we cover the entire value-added chain. Founded in 1941 by brothers Eugen and Martin Hilti, our company builds on strong roots and continuity. This long-term commitment has supported us in becoming a reliable partner for our customers and a trusted brand that they choose to work with. With our defined purpose of “Making Construction Better”, we are committed to developing products and solutions that drive productivity, sustainability, and safety in the construction industry with our values of integrity, courage, teamwork and commitment at the base of everything we do.

Project Description 

Large Project (LP) execution at Hilti faces persistent gaps in long-range material visibility, driven by:

– Limited (>6 months) forecasting accuracy

– Low inclusion of SFDC opportunities into planning tools (only ~20% coverage)

– High BIAS forecast for project essentials (–10.3% in LEC/LW1)

– Incomplete early-stage material signals to suppliers

Resulting supply disruptions, late scheduling, and negative customer experience.

This Master Thesis aims to design and validate a better approach to Large projects planning possibly with the Planning Bill of Materials (pBOM) concept that proactively translates early demand signal, Ex: Segment-Application distribution, Rolling forecast patterns, Project relevant  Sales history, engineering utilization, and SFDC opportunity data—into structured, forecast-ready material visibility.
The work will:

1. Identify gaps in the existing Large project forecast methodology.
2. Validate the existing pBOM engine, including assumptions, forecasting logic, and material aggregation rules.
3. Identify external best practices from industries such as aerospace, automotive, industrial equipment, semiconductors, and construction tech, where Planning/Forecast BOMs are used for long-horizon visibility.
4. Introduce missing theoretical elements (e.g., probabilistic BOM expansion, attribute-based forecasting, confidence scoring, scenario planning, Bayesian updating, multi-signal fusion) that can enhance the accuracy and usability of Hilti’s engine.
5. Develop and test an improved pBOM v2 concept, grounded both in industry benchmarks and Hilti-specific data.

Goals of the Project  

• Validate the current forecasting methodology pBOM v1 engine, including its forecasting logic, material-mapping rules, and underlying assumptions.
• Benchmark Hilti’s pBOM approach against industry and academic best practices in Planning/Forecast BOMs, probabilistic modeling, and long-horizon planning.
• Identify theoretical and methodological gaps that limit pBOM v1 accuracy, stability, or scalability.
• Develop an improved pBOM v2 concept incorporating advanced forecasting theory, signal fusion, and probabilistic BOM structures.
• Build and test analytical prototypes to quantify the improvement potential of pBOM v2 using real historical LP data.
• Collaborate with Hilti IT to convert the conceptual engine into functional technical requirements suitable for an application build.
• Provide strategic recommendations for embedding pBOM v2 into Hilti’s tactical and strategic planning workflows.

Deliverables

• Assessment Report evaluating the current pBOM v1 logic, strengths, limitations, and assumptions.
• Industry & Academic Benchmark Study on Planning/Forecast BOM best practices in project-driven and ETO industries.
• Analytical Gap Analysis identifying missing theoretical elements and improvement areas.
• Enhanced pBOM v2 Concept with refined forecasting and material visibility methodology.
• Prototype or Simulation Model demonstrating pBOM v2 performance using Hilti historical LP data.
• IT Collaboration Output: translation of functional & analytical requirements into technical specifications for the pBOM application build.
• Implementation Recommendations & Rollout Roadmap for operational integration and scaling across regions.
• Final Master’s Thesis Document summarizing methodology, analytics, findings, and strategic recommendations.

Essential Student Knowledge

• Understanding of forecasting and demand planning, including probabilistic or intermittent demand methods.
• Basic knowledge of supply chain planning and BOM structures (Planning/Forecast BOMs, multi-level BOMs).
• Proficiency in data analysis using Python, R, or similar tools.
• Ability to translate business requirements into analytical or technical specifications, especially when collaborating with IT.
• Strong analytical and communication skills to interpret complex datasets and present clear recommendations.

More information: escf@tue.nl