Maximilian Lowin

Mr. Maximilian Lowin

Information Systems and Information Management, Goethe University Frankfurt, Frankfurt am Main, Germany
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
MLMaximilian Lowin
Maximilian Lowin
Introduction: Due to the lack of labeled data, applying predictive maintenance algorithms for facility management is cumbersome. Most companies are unwilling to share data or do not have time for annotation. In addition, most available facility management data are text data. Thus, there is a need for an unsupervised predictive maintenance algorithm that is capable of handling textual data. Methodology: This paper proposes applying association rule mining on maintenance requests to identify upcoming needs in facility management. By coupling temporal association rule mining with the concept of semantic similarity derived from large language models, the proposed methodology can discover meaningful knowledge in the form of rules suitable for decision-making. Results: Relying on the large German language models works best for the presented case study. Introducing a temporal lift filter allows for reducing the created rules to the most important ones. Conclusions: Only a few maintenance requests are sufficient to mine association rules that show links between different infrastructural failures. Due to the unsupervised manner of the proposed algorithm, domain experts need to evaluate the relevance of the specific rules. Nevertheless, the algorithm enables companies to efficiently utilize their data stored in databases to create interpretable rules supporting decision-making.

24 April 2023 in Decision Support Systems
Verified
Journal Article
Closed access
DKDomenic Kellner
Domenic Kellner
MLMaximilian Lowin
Maximilian Lowin
OHOliver Hinz
Oliver Hinz

19 August 2023 in KI - Künstliche Intelligenz
Verified
Journal Article
Open access
PDF file
JCJohannes Chen
Johannes Chen
MLMaximilian Lowin
Maximilian Lowin
DKDomenic Kellner
Domenic Kellner
OHOliver Hinz
Oliver Hinz
EAElisabeth Hannah Adam
Elisabeth Hannah Adam
KWKatharina Wenger-Alakmeh
Katharina Wenger-Alakmeh
One of the most critical infrastructures during the COVID-19 pandemic are intensive care units (ICU). ICU’s crucial task is to preserve the lives of patients and mitigate the pandemic’s impact on the population. However, most ICUs plan only one day ahead. This short-term planning becomes an obstacle during disaster situations since physicians need to decide efficiently and ensure the timely treatment of high-risk patients. Integrating machine learning (ML) systems for clinical decision support could improve this process by predicting the mortality risk of critically ill patients. Several ML approaches tackling this problem have already shown promising results. However, these systems mostly neglect the integration of explicit domain knowledge, which is crucial to ensure prediction quality and adaptability. Otherwise, black-box systems might base their decision on confounding variables and improper relationships. Following design science research, we utilize a unique dataset of patients diagnosed with SARS-CoV-2 in ICU care to design a clinical decision support system by combining ML and expert knowledge in the form of a severity score. We show that by augmenting the system with expert knowledge, its overall performance improves compared to the baseline approach.

1 January 2023 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
MLMaximilian Lowin
Maximilian Lowin
DODana Oz
Dana Oz
ISIris Somech
Iris Somech
MZMoritz von Zahn
Moritz von Zahn
OHOliver Hinz
Oliver Hinz
SRShachar Reichman
Shachar Reichman
Profit-maximizing recommender systems (PMRS) can significantly influence firms’ performance and consumers’ purchasing decisions. However, designing such a recommender system (RS) is a complex task. Merely recommending articles with the highest profit margins could harm the relevance of an article to a customer and, therefore, the purchase probability of a recommendation. This paper aims to explore the multifaceted nature of PMRS and its influence on consumption decisions and firm profitability. We conduct a series of experiments, including laboratory and field experiments at a large online retailer, we examine various PMRS design options and their effects. The results of our study reveal that while a na ̈ıve PMRS may increase profit in a controlled laboratory setting, it does not have a significant effect on profit in real-world field setting compared to a default RS. Even slight variations in settings can disrupt the delicate balance between relevance and profitability. Therefore, we propose a new balanced PMRS with a parameter α that considers the trade-off between an article’s relevance for a customer and its profitability for the firm. In a second randomized field experiment, we show that the balanced PMRS boosts the retailer’s overall profit by more than 20% compared to the default RS. Furthermore, a causal mediation analysis reveals that the balanced PMRS achieves this increase by raising the average price within the customers’ consideration sets.

15 June 2023 in HMD Praxis der Wirtschaftsinformatik
Verified
Journal Article
Open access
PDF file
HKHenrik Kortum
Henrik Kortum
SHSimon Hagen
Simon Hagen
MEMarian Eleks
Marian Eleks
JRJonas Rebstadt
Jonas Rebstadt
FRFlorian Remark
Florian Remark
OTOliver Thomas
Oliver Thomas
Zusammenfassung: Etwa 18 % der CO2-Emissionen in Deutschland entstehen durch die Beheizung, Kühlung und Warmwasserbereitstellung von Gebäuden, wobei mehr als 75 % der deutschen Haushalte fossile Brennstoffe wie Erdgas und Erdöl nutzen. Der in dieser Arbeit vorgestellte SECAI (Sustainable heating through Edge-Cloud-based Artificial Intelligence Systems)-Ansatz verfolgt das Ziel, die Heizungssteuerung in Mehrfamilienhäusern und damit den CO2-Verbrauch durch den Einsatz von Informationstechnologien zu reduzieren.Der SECAI-Ansatz betrachtet dabei das gesamte Ökosystem bestehend aus Sensoren, Einzelraumregelungen, Zentralheizung, Mietenden und Vermietenden. Dabei wird der Heizbedarf von Privatwohnungen KI-basiert analysiert, um darauf aufbauend optimierte und abgestimmte Heizpläne für Gebäudekomplexe und Wohnungen zu erstellen, die in der Lage sind, durch Edge-Cloud-Technologien, Sensorik und Federated Learning ad hoc und datenschutzkonform auf Änderungen im Nutzungsverhalten zu reagieren. Diese Informationen werden zudem für die KI-basierte Steuerung der zentralen Heizanlagen im Gebäude verwendet, in denen Wärme und Warmwasser für alle Wohnungen erzeugt wird. Hierfür betrachtet SECAI vier Ebenen. Diese reichen von Sensoren und Aktoren (Nano), über die Wohnung (Mikro) und das Gebäude (Meso) bis zu Gebäudekomplexen und gleicharten Gebäuden (Makro) und stehen bei der Beheizung in starker Abhängigkeit zueinander. Rund um die SECAI-Lösung entsteht dabei ein komplexes Ökosystem in dem Mietende, die Wohnungswirtschaft, Heizungshersteller und Anbieter von IoT-Lösungen mit Produkten und Diensten in Interaktion treten.

21 May 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
AIAngelo Ippolito
Angelo Ippolito
MLMaximilian Lowin
Maximilian Lowin
JCJohannes Chen
Johannes Chen
MAMaybrit Archner
Maybrit Archner
FRFlorian Jürgen Raimann
Florian Jürgen Raimann
KWKatharina Wenger
Katharina Wenger
Background:Magnetic resonance imaging (MRI) provides higher diagnostic sensitivity than computed tomography (CT) for detecting subtle brain pathology in critically ill patients. However, MRI is resource-intensive and associated with risks during intrahospital transport. Whether MRI performed after an inconclusive CT meaningfully influences clinical management in intensive care unit (ICU) patients remains uncertain. This study evaluated the clinical impact of additional brain MRI and explored whether simple clinical variables could identify patients most likely to benefit. Methods:We conducted a retrospective single-center cohort study of adult ICU patients undergoing brain MRI after an inconclusive CT between 2007 and 2022. The primary outcome was clinical benefit, defined as an MRI-driven change in diagnosis, therapy, level of care, or prognosis. Secondary analyses compared CT accuracy between general radiologists and neuroradiologists and assessed a decision-tree model for predicting MRI benefit. Results:A total of 347 patients were included. MRI was classified as clinically beneficial in 42.9% of cases, although changes in therapy and level of care occurred in only 16.4% and 6.6% of patients, respectively. The decision-tree model achieved a sensitivity of 80% but showed limited overall performance (accuracy 55%, precision 49%, F1-score 61%). Neuroradiologists demonstrated higher CT diagnostic accuracy than general radiologists (56.8% vs 42.7%; p<0.001). Only one transport-related complication occurred. Conclusions:Although MRI frequently detects additional abnormalities after inconclusive CT, its impact on immediate clinical management in ICU patients is limited. Simple predictive modelling was insufficient to guide patient selection. Portable MRI systems may represent a safer and more resource-efficient alternative