Martin, Andreas
E-Mail-Adresse
Geburtsdatum
Suchergebnisse
New hybrid techniques for business recommender systems
Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided, e.g., in consultancy via the use of recommender systems. We explore the special characteristics of such knowledge-based B2B services and propose a process that allows incorporating recommender systems into them. We suggest and compare several recommender techniques that allow incorporating the necessary contextual knowledge (e.g., company demographics). These techniques are evaluated in isolation on a test set of business intelligence consultancy cases. We then identify the respective strengths of the different techniques and propose a new hybridisation strategy to combine these strengths. Our results show that the hybridisation leads to substantial performance improvement over the individual methods.
Hybrid conversational AI for intelligent tutoring systems
We present an approach to improve individual and self-regulated learning in group assignments. We focus on supporting individual reflection by providing feedback through a conversational system. Our approach leverages machine learning techniques to recognize concepts in student utterances and combines them with knowledge representation to infer the student’s understanding of an assignment’s cognitive requirements. The conversational agent conducts end-to-end conversations with the students and prompts them to reflect and improve their understanding of an assignment. The conversational agent not only triggers reflection but also encourages explanations for partial solutions.
Random walks on human knowledge: incorporating human knowledge into data-driven recommenders
We explore the use of recommender systems in business scenarios such as consultancy. In these situations, apart from personal preferences of users, knowledge about objective business-driven criteria plays a role. We investigate strategies for representing and incorporating such knowledge into data-driven recommenders. As a baseline, we choose a robust and flexible paradigm that is based on a simple graph-based representation of past customer cases and choices, in combination with biased random walks. On a real data set from a business intelligence consultancy firm, we study how the incorporation of two important types of explicit human knowledge – namely taxonomic and associative knowledge – impacts the effectiveness of a data-driven recommender. Our results show no consistent improvement for taxonomic knowledge, but quite substantial and significant gains when using associative knowledge.
A new Retrieval Function for Ontology-Based Complex Case Descriptions
This work focuses on case-based reasoning in domains where cases have complex structures with relationships to an arbitrary number of other (potentially complex and structured) entities and where case characterisations (queries) are potentially incomplete. We summarise the requirements for such domains in terms of case representation and retrieval functions. We then analyse properties of existing similarity measures used in CBR { above all symmetry { and argue that some of these properties are not desirable. By exploiting analogies with retrieval functions in the area of information retrieval { where similar functions have been replaced by new ones not exhibiting the aforementioned undesired properties { we derive a new asymmetric ranking function for case retrieval. On a generated test-bed, we show that indeed the new function results in di erent ranking of cases { and use testbed examples to illustrate why this is desirable from a user's perspective.
Practice track: a learning tracker using digital biomarkers for autistic preschoolers
Preschool children, when diagnosed with Autism Spectrum Disorder (ASD), often ex- perience a long and painful journey on their way to self-advocacy. Access to standard of care is poor, with long waiting times and the feeling of stigmatization in many social set- tings. Early interventions in ASD have been found to deliver promising results, but have a high cost for all stakeholders. Some recent studies have suggested that digital biomarkers (e.g., eye gaze), tracked using affordable wearable devices such as smartphones or tablets, could play a role in identifying children with special needs. In this paper, we discuss the possibility of supporting neurodiverse children with technologies based on digital biomark- ers which can help to a) monitor the performance of children diagnosed with ASD and b) predict those who would benefit most from early interventions. We describe an ongoing feasibility study that uses the “DREAM dataset”, stemming from a clinical study with 61 pre-school children diagnosed with ASD, to identify digital biomarkers informative for the child’s progression on tasks such as imitation of gestures. We describe our vision of a tool that will use these prediction models and that ASD pre-schoolers could use to train certain social skills at home. Our discussion includes the settings in which this usage could be embedded.
Visualization of patterns for hybrid learning and reasoning with human involvement
Training and re-using human experience: a recommender for more accurate cost estimates in project planning
In many industries, companies deliver customised solutions to their (business) customers within projects. Estimating the human effort involved in such projects is a difficult task and underestimating efforts can lead to non-billable hours, i.e. financial loss on the side of the solution provider. Previous work in this area has focused on automatic estimation of the cost of software projects and has largely ignored the interaction between automated estimation support and human project leads. Our main hypothesis is that an adequate design of such interaction will increase the acceptance of automatically derived estimates and that it will allow for a fruitful combination of data-driven insights and human experience. We therefore build a recommender that is applicable beyond software projects and that suggests job positions to be added to projects and estimated effort of such positions. The recommender is based on the analysis of similar cases (case-based reasoning), "explains" derived similarities and allows human intervention to manually adjust the outcomes. Our experiments show that recommendations were considered helpful and that the ability of the system to explain and adjust these recommendations was heavily used and increased the trust in the system. We conjecture that the interaction of project leads with the system will help to further improve the accuracy of recommendations and the support of human learning in the future.
ChEdventure - A chatbot-based educational adventure game for modeling tasks in information systems
Practitioners in business information systems are frequently faced with tasks that involve interpretation and representation of organizational information as models, e.g. business processes, the involved participants, and data. Usually, this information comes from varied sources like stakeholders and documents, often resulting in subjective, biased, or incomplete information. Simulating a realistic organizational environment is important for the education of future business process experts, but challenging to achieve in the educational setting. In this work, we propose a chatbot-based educational adventure game that can introduce complex and often contradictory sources of information in a fun learning approach and help the students in abstracting and interpreting this information, constructing models as an outcome. We elaborate on the first design ideas and requirements.
Learning and engineering similarity functions for business recommenders
We study the optimisation of similarity measures in tasks where the computation of similarities is not directly visible to end users, namely clustering and case-based recommenders. In both, similarity plays a crucial role, but there are also other algorithmic components that contribute to the end result. Our suggested approach introduces a new form of interaction into these scenarios that make the use of similarities transparent to end users and thus allows to gather direct feedback about similarity from them. This happens without distracting them from their goal – rather allowing them to obtain better and more trustworthy results by excluding dissimilar items. We then propose to use the feedback in a way that incorporates machine learning for updating weights and decisions of knowledge engineers about possible additional features, based on insights derived from a summary of user feedback. The reviewed literature and our own previous empirical investigations suggest that this is the most feasible way – involving both machine and human, each in a task that they are particularly good at.