Search Results for author: Stefan Feuerriegel

Found 68 papers, 35 papers with code

A Globally Convergent Algorithm for Neural Network Parameter Optimization Based on Difference-of-Convex Functions

1 code implementation15 Jan 2024 Daniel Tschernutter, Mathias Kraus, Stefan Feuerriegel

Furthermore, we mathematically analyze the convergence rate of parameters and the convergence rate in value (i. e., the training loss).

Which linguistic cues make people fall for fake news? A comparison of cognitive and affective processing

no code implementations2 Dec 2023 Bernhard Lutz, Marc Adam, Stefan Feuerriegel, Nicolas Pröllochs, Dirk Neumann

However, little is known about what linguistic cues make people fall for fake news and, hence, how to design effective countermeasures for social media.

Heart Rate Variability

Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework

no code implementations30 Nov 2023 Maresa Schröder, Dennis Frauen, Stefan Feuerriegel

This enables practitioners to examine the sensitivity of their machine learning models to unobserved confounding in fairness-critical applications.

Fairness

A Neural Framework for Generalized Causal Sensitivity Analysis

no code implementations27 Nov 2023 Dennis Frauen, Fergus Imrie, Alicia Curth, Valentyn Melnychuk, Stefan Feuerriegel, Mihaela van der Schaar

We provide theoretical guarantees that NeuralCSA is able to infer valid bounds on the causal query of interest and also demonstrate this empirically using both simulated and real-world data.

Causal Inference valid

Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation

no code implementations19 Nov 2023 Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

In this paper, we propose a new, representation-agnostic framework for estimating bounds on the representation-induced confounding bias that comes from dimensionality reduction (or other constraints on the representations) in CATE estimation.

Dimensionality Reduction Representation Learning

Counterfactual Fairness for Predictions using Generative Adversarial Networks

no code implementations26 Oct 2023 Yuchen Ma, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel

It is often achieved through counterfactual fairness, which ensures that the prediction for an individual is the same as that in a counterfactual world under a different sensitive attribute.

Attribute counterfactual +2

Causal Understanding of Why Users Share Hate Speech on Social Media

no code implementations24 Oct 2023 Dominique Geissler, Abdurahman Maarouf, Stefan Feuerriegel

Hate speech on social media threatens the mental and physical well-being of individuals and is further responsible for real-world violence.

Causal Inference Selection bias

DSG: An End-to-End Document Structure Generator

1 code implementation13 Oct 2023 Johannes Rausch, Gentiana Rashiti, Maxim Gusev, Ce Zhang, Stefan Feuerriegel

To the best of our knowledge, our DSG system is the first end-to-end trainable system for hierarchical document parsing.

Optical Character Recognition (OCR)

Generative AI

no code implementations13 Sep 2023 Stefan Feuerriegel, Jochen Hartmann, Christian Janiesch, Patrick Zschech

Based on that, we introduce limitations of current generative AI and provide an agenda for Business & Information Systems Engineering (BISE) research.

Data-Driven Allocation of Preventive Care With Application to Diabetes Mellitus Type II

no code implementations14 Aug 2023 Mathias Kraus, Stefan Feuerriegel, Maytal Saar-Tsechansky

In this paper, we develop a data-driven decision model for determining a cost-effective allocation of preventive treatments to patients at risk.

counterfactual Counterfactual Inference +2

Analyzing the Strategy of Propaganda using Inverse Reinforcement Learning: Evidence from the 2022 Russian Invasion of Ukraine

no code implementations24 Jul 2023 Dominique Geissler, Stefan Feuerriegel

The 2022 Russian invasion of Ukraine was accompanied by a large-scale, pro-Russian propaganda campaign on social media.

Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model

1 code implementation NeurIPS 2023 Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

We further show that existing point counterfactual identification methods are special cases of our Curvature Sensitivity Model when the bound of the curvature is set to zero.

counterfactual Counterfactual Inference

Addressing distributional shifts in operations management: The case of order fulfillment in customized production

1 code implementation24 Apr 2023 Julian Senoner, Bernhard Kratzwald, Milan Kuzmanovic, Torbjørn H. Netland, Stefan Feuerriegel

We empirically validate our proposed approach using real-world data from a job shop production that supplies large metal components to an oil platform construction yard.

Decision Making Job Shop Scheduling +2

Fair Off-Policy Learning from Observational Data

no code implementations15 Mar 2023 Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel

Algorithmic decision-making in practice must be fair for legal, ethical, and societal reasons.

Decision Making Fairness +1

QA Domain Adaptation using Hidden Space Augmentation and Self-Supervised Contrastive Adaptation

1 code implementation19 Oct 2022 Zhenrui Yue, Huimin Zeng, Bernhard Kratzwald, Stefan Feuerriegel, Dong Wang

Unlike existing approaches, we generate pseudo labels and propose to train the model via a novel attention-based contrastive adaptation method.

Contrastive Learning Data Augmentation +2

Normalizing Flows for Interventional Density Estimation

1 code implementation13 Sep 2022 Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

To the best of our knowledge, our Interventional Normalizing Flows are the first proper fully-parametric, deep learning method for density estimation of potential outcomes.

Causal Inference Density Estimation

Estimating individual treatment effects under unobserved confounding using binary instruments

1 code implementation17 Aug 2022 Dennis Frauen, Stefan Feuerriegel

(2)~We further show that our framework asymptotically outperforms state-of-the-art plug-in IV methods for CATE estimation, in the sense that it achieves a faster rate of convergence if the CATE is smoother than the individual outcome surfaces.

Locating disparities in machine learning

1 code implementation13 Aug 2022 Moritz von Zahn, Oliver Hinz, Stefan Feuerriegel

As a result, ALD helps practitioners and researchers of algorithmic fairness to detect disparities in machine learning algorithms, so that disparate -- or even unfair -- outcomes can be mitigated.

Attribute Fairness

Algorithmic Fairness in Business Analytics: Directions for Research and Practice

no code implementations22 Jul 2022 Maria De-Arteaga, Stefan Feuerriegel, Maytal Saar-Tsechansky

The extensive adoption of business analytics (BA) has brought financial gains and increased efficiencies.

Fairness

Contrastive Learning for Unsupervised Domain Adaptation of Time Series

1 code implementation13 Jun 2022 Yilmazcan Ozyurt, Stefan Feuerriegel, Ce Zhang

To the best of our knowledge, ours is the first framework to learn domain-invariant, contextual representation for UDA of time series data.

Contrastive Learning Time Series +2

Causal Transformer for Estimating Counterfactual Outcomes

1 code implementation14 Apr 2022 Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel

In this paper, we develop a novel Causal Transformer for estimating counterfactual outcomes over time.

counterfactual

Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine

1 code implementation14 Apr 2022 Theresa Blümlein, Joel Persson, Stefan Feuerriegel

Common methods for learning optimal DTRs, however, have shortcomings: they are typically based on outcome prediction and not treatment effect estimation, or they use linear models that are restrictive for patient data from modern electronic health records.

Web Mining to Inform Locations of Charging Stations for Electric Vehicles

1 code implementation10 Mar 2022 Philipp Hummler, Christof Naumzik, Stefan Feuerriegel

To address our research question, we propose the use of web mining: we characterize the influence of different POIs from OpenStreetMap on the utilization of charging stations.

Interpretable Off-Policy Learning via Hyperbox Search

1 code implementation4 Mar 2022 Daniel Tschernutter, Tobias Hatt, Stefan Feuerriegel

Using a simulation study, we demonstrate that our algorithm outperforms state-of-the-art methods from interpretable off-policy learning in terms of regret.

Estimating Conditional Average Treatment Effects with Missing Treatment Information

1 code implementation2 Mar 2022 Milan Kuzmanovic, Tobias Hatt, Stefan Feuerriegel

Although this is a widespread problem in practice, CATE estimation with missing treatments has received little attention.

Domain Adaptation

Estimating average causal effects from patient trajectories

1 code implementation2 Mar 2022 Dennis Frauen, Tobias Hatt, Valentyn Melnychuk, Stefan Feuerriegel

In medical practice, treatments are selected based on the expected causal effects on patient outcomes.

Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects

1 code implementation25 Feb 2022 Tobias Hatt, Jeroen Berrevoets, Alicia Curth, Stefan Feuerriegel, Mihaela van der Schaar

While observational data is confounded, randomized data is unconfounded, but its sample size is usually too small to learn heterogeneous treatment effects.

Representation Learning

Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxies

1 code implementation6 Dec 2021 Milan Kuzmanovic, Tobias Hatt, Stefan Feuerriegel

To this end, we develop the Deconfounding Temporal Autoencoder, a novel method that leverages observed noisy proxies to learn a hidden embedding that reflects the true hidden confounders.

Decision Making valid

Generalizing Off-Policy Learning under Sample Selection Bias

no code implementations2 Dec 2021 Tobias Hatt, Daniel Tschernutter, Stefan Feuerriegel

Since training data is often not representative of the target population, standard policy learning methods may yield policies that do not generalize target population.

Selection bias

A Sociotechnical View of Algorithmic Fairness

no code implementations27 Sep 2021 Mateusz Dolata, Stefan Feuerriegel, Gerhard Schwabe

We contribute as follows: First, we problematize fundamental assumptions in the current discourse on algorithmic fairness based on a systematic analysis of 310 articles.

Decision Making Fairness

Contrastive Domain Adaptation for Question Answering using Limited Text Corpora

1 code implementation EMNLP 2021 Zhenrui Yue, Bernhard Kratzwald, Stefan Feuerriegel

Here, we train a QA system on both source data and generated data from the target domain with a contrastive adaptation loss that is incorporated in the training objective.

Domain Adaptation Question Answering +2

Sequential Deconfounding for Causal Inference with Unobserved Confounders

1 code implementation16 Apr 2021 Tobias Hatt, Stefan Feuerriegel

In this paper, we develop the Sequential Deconfounder, a method that enables estimating individualized treatment effects over time in presence of unobserved confounders.

Causal Inference Decision Making

AttDMM: An Attentive Deep Markov Model for Risk Scoring in Intensive Care Units

1 code implementation9 Feb 2021 Yilmazcan Özyurt, Mathias Kraus, Tobias Hatt, Stefan Feuerriegel

In this work, we propose a novel generative deep probabilistic model for real-time risk scoring in ICUs.

Directed particle swarm optimization with Gaussian-process-based function forecasting

no code implementations8 Feb 2021 Johannes Jakubik, Adrian Binding, Stefan Feuerriegel

Particle swarm optimization (PSO) is an iterative search method that moves a set of candidate solution around a search-space towards the best known global and local solutions with randomized step lengths.

Bayesian Optimization Evolutionary Algorithms

Estimating Average Treatment Effects via Orthogonal Regularization

1 code implementation21 Jan 2021 Tobias Hatt, Stefan Feuerriegel

In this paper, we propose a novel regularization framework for estimating average treatment effects that exploits unconfoundedness.

Decision Making

Monitoring the COVID-19 epidemic with nationwide telecommunication data

1 code implementation7 Jan 2021 Joel Persson, Jurriaan F. Parie, Stefan Feuerriegel

We derive human mobility from anonymized, aggregated telecommunication data in a nationwide setting (Switzerland; February 10 - April 26, 2020), consisting of ~1. 5 billion trips.

Applications

Estimating Treatment Effects via Orthogonal Regularization

no code implementations1 Jan 2021 Tobias Hatt, Stefan Feuerriegel

Based on our regularization framework, we develop deep orthogonal networks for unconfounded treatments (DONUT) which learn outcomes that are orthogonal to the treatment assignment.

Causal Inference Decision Making

Learning Active Learning in the Batch-Mode Setup with Ensembles of Active Learning Agents

no code implementations1 Jan 2021 Malte Ebner, Bernhard Kratzwald, Stefan Feuerriegel

As this approach can incorporate any active learning agent into its ensemble, it allows to increase the performance of every active learning agent by learning how to combine it with others.

Active Learning Reinforcement Learning (RL)

IntKB: A Verifiable Interactive Framework for Knowledge Base Completion

1 code implementation COLING 2020 Bernhard Kratzwald, Guo Kunpeng, Stefan Feuerriegel, Dennis Diefenbach

(ii) Our system is designed such that it continuously learns during the KB completion task and, therefore, significantly improves its performance upon initial zero- and few-shot relations over time.

Knowledge Base Completion Question Answering

Estimating Risk-Adjusted Hospital Performance

1 code implementation10 Nov 2020 Eva van Weenen, Stefan Feuerriegel

These findings demonstrate that a large portion of the variance in health outcomes can be attributed to non-linear relationships between patient risk variables and implicate that the current approach of measuring hospital performance should be expanded.

Learning a Cost-Effective Annotation Policy for Question Answering

1 code implementation EMNLP 2020 Bernhard Kratzwald, Stefan Feuerriegel, Huan Sun

State-of-the-art question answering (QA) relies upon large amounts of training data for which labeling is time consuming and thus expensive.

Question Answering

Practical Annotation Strategies for Question Answering Datasets

no code implementations6 Mar 2020 Bernhard Kratzwald, Xiang Yue, Huan Sun, Stefan Feuerriegel

Here, remarkably, annotating a stratified subset with only 1. 2% of the original training set achieves 97. 7% of the performance as if the complete dataset was annotated.

Question Answering

DocParser: Hierarchical Structure Parsing of Document Renderings

2 code implementations5 Nov 2019 Johannes Rausch, Octavio Martinez, Fabian Bissig, Ce Zhang, Stefan Feuerriegel

Translating renderings (e. g. PDFs, scans) into hierarchical document structures is extensively demanded in the daily routines of many real-world applications.

Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences

no code implementations11 Jul 2019 Mathias Kraus, Stefan Feuerriegel

This demonstrates the performance and superior interpretability of our method, while we finally discuss implications for decision support.

BIG-bench Machine Learning

RankQA: Neural Question Answering with Answer Re-Ranking

1 code implementation ACL 2019 Bernhard Kratzwald, Anna Eigenmann, Stefan Feuerriegel

The conventional paradigm in neural question answering (QA) for narrative content is limited to a two-stage process: first, relevant text passages are retrieved and, subsequently, a neural network for machine comprehension extracts the likeliest answer.

Question Answering Reading Comprehension +2

Learning Interpretable Negation Rules via Weak Supervision at Document Level: A Reinforcement Learning Approach

no code implementations NAACL 2019 Nicolas Pr{\"o}llochs, Stefan Feuerriegel, Dirk Neumann

For this, we present a novel strategy for learning fully interpretable negation rules via weak supervision: we apply reinforcement learning to find a policy that reconstructs negation rules from sentiment predictions at document level.

Negation Sentiment Analysis

Personalized Purchase Prediction of Market Baskets with Wasserstein-Based Sequence Matching

1 code implementation24 May 2019 Mathias Kraus, Stefan Feuerriegel

In contrast, our research overcomes the limitations of pre-set rules by contributing a novel predictor of market baskets from sequential purchase histories: our predictions are based on similarity matching in order to identify similar purchase habits among the complete shopping histories of all customers.

Dynamic Time Warping Marketing +1

Sample Complexity Bounds for Recurrent Neural Networks with Application to Combinatorial Graph Problems

no code implementations29 Jan 2019 Nil-Jana Akpinar, Bernhard Kratzwald, Stefan Feuerriegel

As our primary contribution, this is the first work that upper bounds the sample complexity for learning real-valued RNNs.

Reinforcement Learning in R

no code implementations29 Sep 2018 Nicolas Pröllochs, Stefan Feuerriegel

Reinforcement learning refers to a group of methods from artificial intelligence where an agent performs learning through trial and error.

Q-Learning reinforcement-learning +1

Adaptive Document Retrieval for Deep Question Answering

1 code implementation EMNLP 2018 Bernhard Kratzwald, Stefan Feuerriegel

State-of-the-art systems in deep question answering proceed as follows: (1) an initial document retrieval selects relevant documents, which (2) are then processed by a neural network in order to extract the final answer.

Question Answering Retrieval

News-based trading strategies

no code implementations18 Jul 2018 Stefan Feuerriegel, Helmut Prendinger

The marvel of markets lies in the fact that dispersed information is instantaneously processed and used to adjust the price of goods, services and assets.

Decision Making Reinforcement Learning (RL)

Deep learning in business analytics and operations research: Models, applications and managerial implications

no code implementations28 Jun 2018 Mathias Kraus, Stefan Feuerriegel, Asil Oztekin

(4) We provide guidelines and implications for researchers, managers and practitioners in operations research who want to advance their capabilities for business analytics with regard to deep learning.

BIG-bench Machine Learning

Investor Reaction to Financial Disclosures Across Topics: An Application of Latent Dirichlet Allocation

no code implementations8 May 2018 Stefan Feuerriegel, Nicolas Pröllochs

This paper provides a holistic study of how stock prices vary in their response to financial disclosures across different topics.

Putting Question-Answering Systems into Practice: Transfer Learning for Efficient Domain Customization

no code implementations19 Apr 2018 Bernhard Kratzwald, Stefan Feuerriegel

Traditional information retrieval (such as that offered by web search engines) impedes users with information overload from extensive result pages and the need to manually locate the desired information therein.

Information Retrieval Management +3

News-based forecasts of macroeconomic indicators: A semantic path model for interpretable predictions

no code implementations22 Jan 2018 Stefan Feuerriegel, Julius Gordon

The macroeconomic climate influences operations with regard to, e. g., raw material prices, financing, supply chain utilization and demand quotas.

Feature Engineering Time Series +1

Statistical Inferences for Polarity Identification in Natural Language

no code implementations21 Jun 2017 Nicolas Pröllochs, Stefan Feuerriegel, Dirk Neumann

Information forms the basis for all human behavior, including the ubiquitous decision-making that people constantly perform in their every day lives.

Decision Making Marketing

Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees

no code implementations18 Apr 2017 Mathias Kraus, Stefan Feuerriegel

To learn from the resulting rhetorical structure, we propose a tensor-based, tree-structured deep neural network (named Discourse-LSTM) in order to process the complete discourse tree.

Data Augmentation Marketing +1

Understanding Negations in Information Processing: Learning from Replicating Human Behavior

no code implementations18 Apr 2017 Nicolas Pröllochs, Stefan Feuerriegel, Dirk Neumann

Information systems experience an ever-growing volume of unstructured data, particularly in the form of textual materials.

Recommendation Systems

Improving Decision Analytics with Deep Learning: The Case of Financial Disclosures

no code implementations9 Aug 2015 Stefan Feuerriegel, Ralph Fehrer

Decision analytics commonly focuses on the text mining of financial news sources in order to provide managerial decision support and to predict stock market movements.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.