Award winners 2022

Stefan Schwarze: Solution Methods for Discrete Nash Equilibrium Problems

About the masterthesis: We study non-cooperative n-person games, where each player aims to maximize her payoff given the other players' strategies. Applied to competing firms in a market, the equilibrium points are interesting for the firms as well as for a central authority that may pose rules. Up to now, most algorithmic approaches for the computation of Nash equilibria require continuous strategy sets for all players. However, integer decisions appear in many real-world applications. We present a branch-and-prune procedure for discrete Nash equilibrium problems with a convex description of each player’s strategy set. The derived pruning criterion reduces the search space effectively by stating the activity of certain constraints. This results in a synchronous branching and pruning method.

1-minute video-explanation on the thesis​

Lukas Struppek: Embedding Convolutional Mixture of Experts into Deep Neural Networks for Computer Vision Tasks

About the masterthesis: The Mixture of Experts (MoE) concept is based on the idea of using different expert models for various tasks, which are dynamically selected by a so-called gating network. This work incorporates the MoE concept in the form of generic MoE layers into deep Convolutional Neural Networks for image processing. It is demonstrated that even with a single dataset and end-to-end learning, which traditional MoE approaches do not support, there is an implicit specialization of individual experts in specific domains. This provides additional insights into the decision-making process within neural networks. Furthermore, the number of active experts can be dynamically determined and scaled according to the available computational power.

 1-minute video-explanation on the thesis

Kevin Wiegratz: Machine Learning Methods in Financial Economics: Recent Applications, Prospects, and the Valuation of Real Estate Assets

About the masterthesis: Artificial intelligence is increasingly entering our day-to-day life with impressive applications such as face detection or voice recognition. The main technology behind artificial intelligence is machine learning (ML). Given the power of ML, this thesis investigates where and how to apply ML in financial economics. First, the thesis identifies the methodological differences of ML compared to traditional econometric approaches. Then, it develops a taxonomy of existing and future applications of ML in financial economics. Finally, it applies ML to a typical problem in financial economics: the pricing of real estate assets. The results show a significant improvement of ML over traditional methods, which demonstrates the strong potential of ML for future applications in financial economics.

Award winners 2021

Patrick Mark Deininger: Monte Carlo Tree Search for Production Scheduling in Matrix Production

About the masterthesis: A challenge in the production control of matrix productions is the real-time generation of effective machine allocation plans, which is an NP-hard problem. Patrick Deininger developed a central, holistic decision-making entity that utilizes multi-criteria Monte Carlo Tree Search (MCTS) to determine Pareto solutions in real-time while considering individual preferences. The paper considers two modifications of MCTS, among other things. (1) Dynamic adaptation of exploration and exploitation enhances local optima. (2) Learning promising combination rules for action generation enables adaptability to changing optimization contexts and significantly improves generalizability, search speed, and solution quality.

1-minute video-explanation on the thesis

Patrick Hemmer: DEAL: Deep Evidential Active Learning for Image Classification

Über die Masterarbeit: Convolutional Neural Networks (CNNs) have proven to be state-of-the-art models for supervised computer vision tasks. However, large labeled data sets are generally needed for model training. Unlabeled data is available in many domains, but labeling is expensive, e.g., when specific expert knowledge is required. In this thesis, a novel Active Learning algorithm that learns from unlabeled data by capturing high prediction uncertainty is proposed to mitigate the problem of extensive data labeling. We demonstrate with publicly available data and in the context of a quality assurance industry use case that our approach leads to a significant reduction in the number of labeled images necessary to achieve a predefined performance contributing to a considerable decrease in labeling overhead.

1-minute video-explanation on the thesis

Jingyi Lisa Zhang:Overcoming the Cold Start Problem in AI Technology - A Survey-based Approach on Example of Wearable Sleep Tracker AURA

Über die Masterarbeit: Wearable sleep technology such as AURA represents a novel technology that promises to deliver the most accurate sleep measurement as well as sleeping improvement suggestions and thus generates benefits for customers in need. However, there is a critical time period between users’ first interaction and the first valid piece of sleep-improving suggestion the algorithm can generate due to development of statistical significance which hence, leads to unclear acceptance of customers. After relevant case study, this work aims to explore various value perception and expectation of possible segments in terms of their preferences in sleep wearable area, in particular regarding the critical initial phase (“cold start”). First, the experimental study reveals users’ implicit valuations via conjoint analysis. Attributes of Design, measured sleep parameter and frequency of necessary input are the most important in a nutshell. The study also provides empirical evidence for the existence of three dissimilar clusters, that is, design preferred lifestylers, indifferent average followers and detail-oriented functional desirers. The findings imply different strategies of recommended course of action regarding the relevance of the cold start problem. Finally, implications are discussed and future research options are sketched out.