..
/ cps / home /
 

Marco Fries

Marco Fries
Email: marco.fries(at)uni-siegen.de 

 

Room: US-D 117 (Ludwig-Wittgenstein-Haus, Campus Unteres Schloss)

Phone:  +49 (0) 271 / 740 5165

Consultation hour: By arrangement

Vita

Marco Fries studied Business Information Systems at the University of Siegen. Parallel to his studies, he was employed by GIB mbH as a dual student. GIB mbH is active in the area of software development around SAP with its own products. He also wrote his Bachelor’s thesis at this company. After successfully completing his Bachelor’s degree, he first worked as a software developer and later as a consultant and project manager at the same company.

After two years of full-time work, he started a Master’s degree in Human Computer Interaction at the University of Siegen on a half-time basis. His master’s thesis focused on sales planning and machine learning with the title: “A design case study for sales forecasting using machine learning in the food industry”.

After two more years as a department head for global consulting, academy and support, he started at the University of Siegen in August 2021 as a research assistantat the Chair of Cyber-Physical Systems. Here he is involved in the ExPro project and in supporting a project to develop a regional future centre for artificial intelligence.

Publications

2022


  • Fries, M. & Ludwig, T. (2022)‘Why are the Sales Forecasts so low?’ Socio-Technical Challenges of Using Machine Learning for Forecasting Sales in a Bakery

    IN Computer Supported Cooperative Work (CSCW) doi:10.1007/s10606-022-09458-z
    [BibTeX] [Abstract] [Download PDF]
    Artificial intelligence and the underlying machine learning (ML) methods are increasingly finding their way into our working world. One of these areas is sales planning, where machine learning is used to leverage a variety of different input parameters such as prices, promotions, or the weather, to forecast sales, and therefore directly affects the production of products and goods. To satisfy the goal of environmental sustainability as well as address short shelf life, the food industry represents an interesting application field for the use of ML for optimizing sales planning. Within this paper, we will examine the design, and especially the application, of ML methods in the food industry and show the current challenges that exist in the use of such concepts and technologies from the end-user’s point of view. Our study of a smaller bakery company shows that there are enormous challenges in setting up the appropriate infrastructure and processes for the implementation of ML, that the output quality of ML processes does not always match the perceived result quality, and that trust in the functioning of the algorithms is the most important criterion for using ML processes in practice.
    @article{fries_why_2022,
    title = {‘{Why} are the {Sales} {Forecasts} so low?’ {Socio}-{Technical} {Challenges} of {Using} {Machine} {Learning} for {Forecasting} {Sales} in a {Bakery}},
    issn = {1573-7551},
    shorttitle = {‘{Why} are the {Sales} {Forecasts} so low?},
    url = {https://doi.org/10.1007/s10606-022-09458-z},
    doi = {10.1007/s10606-022-09458-z},
    abstract = {Artificial intelligence and the underlying machine learning (ML) methods are increasingly finding their way into our working world. One of these areas is sales planning, where machine learning is used to leverage a variety of different input parameters such as prices, promotions, or the weather, to forecast sales, and therefore directly affects the production of products and goods. To satisfy the goal of environmental sustainability as well as address short shelf life, the food industry represents an interesting application field for the use of ML for optimizing sales planning. Within this paper, we will examine the design, and especially the application, of ML methods in the food industry and show the current challenges that exist in the use of such concepts and technologies from the end-user’s point of view. Our study of a smaller bakery company shows that there are enormous challenges in setting up the appropriate infrastructure and processes for the implementation of ML, that the output quality of ML processes does not always match the perceived result quality, and that trust in the functioning of the algorithms is the most important criterion for using ML processes in practice.},
    language = {en},
    urldate = {2022-12-19},
    journal = {Computer Supported Cooperative Work (CSCW)},
    author = {Fries, Marco and Ludwig, Thomas},
    month = dec,
    year = {2022},
    keywords = {Artificial Intelligence, Human-AI Interaction, Human–Computer Interaction, Machine Learning, Sales Forecast},
    }