Back to TUM-PREP Projects overview

Project Overview

Project Code: MGT 01

Project name:

Transfer learning for demand forecasting and inventory optimization in print media distribution

TUM Department:

MGT – School of Management

TUM Chair / Institute:

Chair of Logistics and Supply Chain Management

Research area:

Machine Learning/Operations Research

Student background:

Computer Science/ InformaticsManagement / Economics

Further disciplines:

Participation also possible online only:

Planned project location:

Arcisstraße 21
80333 Munich, Germany

Project Supervisor - Contact Details


Title:

Prof. Dr.

Given name:

Stefan

Family name:

Minner

E-mail:

stefan.minner@tum.de

Phone:

+49 (0)89 289 28201

Additional Project Supervisor - Contact Details


Title:

M.Sc.

Given name:

Till Nikolaus

Family name:

Krieger

E-mail:

till.krieger@tum.de

Phone:

Additional Project Supervisor - Contact Details


Title:

Given name:

Family name:

E-mail:

Phone:

Project Description


Project description:

Background
The Chair of Logistics and Supply Chain Management launched a research project with a company in the newspaper/magazine sector.
The TUM PREP project will focus on demand forecasting and inventory optimization. The objective is to use Big Data and Machine Learning to improve forecasting accuracy and inventory management in print media distribution.

Project
Demand forecasting is essential for making informed inventory decisions, reducing costs, and increasing customer satisfaction. In this project the focus will be on the concept of transfer learning.
Transfer learning involves using models that have been pretrained on similar or diverse source datasets to leverage existing knowledge for new tasks. By fine-tuning these models on the target dataset, their accuracy and relevance can be significantly improved. This approach allows the models to adapt to specific features of the target data. Additionally, pretrained models can be applied directly to produce forecasts without further training, known as zero-shot learning, enabling immediate and efficient predictions.

Requirements
Proficiency in Python programming is required. A keen interest in data analytics and machine learning is crucial. The interest in working in a industry-related project is recommended.

This project offers an exciting opportunity to explore the intersection of demand forecasting, 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:

Other:

  • Keine Stichwörter