Thesis Student Supply Chain Science (d/f/m) - Hamburg

Our 4flow research team conducts exciting research projects, develops innovative digitalization solutions and creates market-relevant studies in the field of supply chain management and logistics.

Support us full-time as a Bachelor’s or Master’s student as part of your thesis project!

What your new challenge will look like

As a Bachelor’s or Master’s student:

• You’ll support the 4flow research team in application-oriented studies.
• You’ll work on scientific questions from data preparation and analysis to modeling, evaluation, and interpretation. Always in close collaboration with our experienced logistics researchers.
• You’ll process data from various sources and expert interviews and integrate them into a scalable analysis pipeline.
• You’ll implement models in Python (or similar) and evaluate their quality using established metrics.
• You’ll collaborate closely with our data scientists and logistics researchers, exchange ideas regularly and ensure a smooth knowledge transfer within the team.

Current thesis topics include:

Inventory Optimization in Multi-Tier Supply Chains

Reducing inventory can lead to significant cost savings. However, to ensure delivery reliability in volatile environments, inventory is essential at various stages of the supply chain. This topic focuses on developing and enhancing methods for holistic inventory optimization, considering uncertain lead and replenishment times. The goal is to ensure practical applicability by integrating diverse industry-specific characteristics.

AI-Driven Transparency in Inbound Supply Chains for Risk Management

Lack of visibility beyond Tier-1 suppliers makes inbound supply chains vulnerable to unforeseen risks and delays proactive action. This topic aims to develop an innovative ML/GenAI framework that automatically predicts geographic waypoints and transport modes, enabling data-driven insights to support inbound logistics management.

Model for Predicting Logistics Infrastructure Usage in Transportation

Limited transparency regarding logistics hubs used within supply chain routes leads to delayed risk detection and missed optimization opportunities. This topic involves developing an ML/GenAI framework that automatically predicts transshipment points and connections based on known origin-destination pairs, strengthening logistics planning through data-driven decision support.