Markus Rosenfelder

EDV-Beauftragter der Wirtschaftswissenschaftlichen Fakultät

Auszeichnung für eine hervorragende Master-Thesis, Albert-Ludwigs-Universität Freiburg & Deutsche Immobilien-Akademie der Universität Freiburg

• Übung: Wirtschaftsinformatik für die Unternehmensführung: “Optimization and Simulation”

• Seminar: Einführung in die Programmierung: Python Programmierung anhand praxisnaher Beispiele

• Seminar: Einführung in die Programmierung: Python Programmierung anhand praxisnaher Beispiele

• Seminar: Einführung in die Programmierung: Python Programmierung anhand praxisnaher Beispiele
• Workshop für Doktoranden: Web-scraping in Python
• Vorlesung: Data Science (Hochschule Fresenius)

• Übung: Wirtschaftsinformatik für die Unternehmensführung: “Optimization and Simulation”
• Seminar: Data Analytics in R and Python 

• Übung: Business Intelligence
• Seminar: Business Intelligence in R and Python

Forschungsaufenthalt am National Institute for Environmental Studies in
Tsukuba, Japan

Doktorand am Lehrstuhl für Wirtschaftsinformatik, Albert-Ludwigs-Universität Freiburg

Master of Science in Volkswirtschaftslehre, Albert-Ludwigs-Universität Freiburg
Thesis: „Rising High: Improving Real Estate Valuation with 3D City Models and Spatial Analytics“

Bachelor of Science in Volkswirtschaftslehre, Albert-Ludwigs Universität Freiburg
Thesis: „Geo-spatial analysis of different car types in free-floating carsharing | Betreuer: Prof. Dr. Neumann

10/2017 – 02/2018

Studentische Hilfskraft am Lehrstuhl für Wirtschaftsinformatik, Albert-Ludwigs-Universität
Tutor für „Management of Information Systems: Einführung in die Wirtschaftsinformatik“

10/2016 – 12/2017

Werkstudent bei Geospin GmbH
Programmiertätigkeiten im Bereich Data Science mit Geodaten-Bezug

Studentische Hilfskraft am Lehrstuhl für Wirtschaftsinformatik, Albert-Ludwigs-Universität
IT und Systemadministration

• Deep Learning in Real Estate: Using Convolutional Neural Networks to improve Real Estate Valuations
• Machine Learning for Predictive Policing: Spatio-temporal Data Analysis of Criminal Hotspots
• Creating knowledge by mining multi-source big data in transport. Case study in Thessaloniki 
• Creating an Edge: Predicting Stock Prices with Sentiment Analysis
• Maschinelles Lernen: Probabilistische Methoden in der wirtschaftlichen Anwendung
• Applied Machine Learning in Economics: Predicting Real Estate Prices in Munich
• Spatio-temporal Modeling: Analyzing Street Crime in Detroit
• Failed Cities: Spatial Analysis of Street Crime in Detroit
• Data Mining: Hyperparameter Optimization for Real Estate Prediction Models
• What determines effective political communication? An empirical analysis of language patterns on Twitter
• Realizing the Power of Aerial Image Data through Deep Learning: A Real Estate Case Study
• Optimizing Bug Classifications with Bidirectional Encoder Representations from Transformers
• Machine Learning in Real Estate: Accurate Rent Price Prediction with Natural Language Processing and Gradient Boosting
• Applied Machine Learning: Improving Real Estate Price Predictions with Natural Language Processing and Bayesian Optimization
• Semi-Supervised Deep Learning for Real Estate Price Predictions using Image Segmentation and Convolutional Neural Networks
• Understanding the Power of Political Communication through Machine Learning: An in-depth Sentiment Analysis of Twitter Messages of German Politicians
• Learning from Failure: Econometric Insights into Kickstarter Crowdfunding Campaigns
• Multi-objective Re-Ranking of Recommendations: A Machine Learning Approach
• Understanding the Potential Influence of Socio-Demographic Data on Renewable Energy Installations in Germany through Statistical Learning
• Climate Change Mitigation: Prediction of Energy Consumption of Buildings with Ensemble Machine Learning
• Climate Change and AI: Prediction of Building Energy Consumption with Artificial Neural Networks
• Real Estate Valuation and AI: Prediction of Housing Prices with Deep Neural Networks and Gradient Boosting Machines
• Building Energy Consumption Research with Machine Learning: Analysis of Residential Housing in Florida