Back to TUM-PREP Projects overview

Project Overview

Project Code: MGT 01

Project name:

End-to-End Machine Learning for Data-Driven Inventory Control

TUM Department:

MGT – School of Management

TUM Chair / Institute:

Logistics and Supply Chain Management

Research area:

Operations and Technology

Student background:

Computer EngineeringComputer Science/ InformaticsManagement / EconomicsMathematics

Further disciplines:

Participation also possible online only:

Planned project location:

Arcisstr. 21
80333 Munich

Project Supervisor - Contact Details


Title:

Prof. Dr.

Given name:

Stefan

Family name:

Minner

E-mail:

stefan.minner@tum.de

Phone:

+49 89 289 28201

Additional Project Supervisor - Contact Details


Title:

Given name:

Patrick

Family name:

Helm

E-mail:

patrick.helm@tum.de

Phone:

+49 89 289 28202

Additional Project Supervisor - Contact Details


Title:

Given name:

Family name:

E-mail:

Phone:

Project Description


Project description:

Background:
Inventory control is essential for all companies dealing with physical goods and thus a main driver of supply chain performance. The traditional approach of predict-then-optimize involves forecasting and replenishment planning as two sequential steps. However, the evidence accumulates that this approach is insufficient for complex inventory control problems. Instead, data-driven optimization leverages cutting-edge machine learning methods to optimize inventories directly from past demand data. For example, Amazon switched its inventory control algorithm from classical forecasting + inventory planning methods to an end-to-end data-driven machine learning pipeline and thus achieved significant cost reduction.

Project:
This TUM PREP project focuses on building a machine learning pipeline that can directly control inventory from past demand observations without requiring forecasting as an intermediate step. A large-scale real-world demand data set will be provided. The project offers an exciting opportunity to explore the intersection of big data and machine learning, with a focus on improving inventory decisions.

Working hours per week planned:

40

Prerequisites


Required study level minimum (at time of TUM PREP project start):

2 years of bachelor studies completed

Subject related:

Proficiency in Python programming is required. Basic knowledge of supervised learning and/or reinforcement learning is expected. A keen interest in data analytics and working with real-world data is crucial.

Other:

  • Keine Stichwörter