Colloquium IS (February 2, 2018)

Dear all,

We are pleased to invite you to our next Colloquium IS that will take place on Friday,

February 2, 2018, 12:30 – 13:30 (Paviljoen K.16).

Speaker: Maryam Razavian

Title: Empirical Research Design for Software Architecture Decision Making:
An Analysis

Abstract: Software architecture decision making involves humans, their behavioral issues and practice. As such, research on decision making needs to involve not only engineering but social science research methods. Despite past empirical research in software architecture decision making, we have not systematically studied how to perform such empirical research.

This talk is about the research methods have been used to study human decision making in software architecture. We analyzed research papers from our literature review on software architecture decision making. We classified the papers according to different facets of empirical research design like research logic, research purpose, research methodology and process. We derive lessons learned from existing studies and discuss open research issues inspired by social science research. We found predominant choices for the strategic research design and a variety of tactical design, operational design and study foci. We therefore introduce the focus matrix and the decision making research cycle to help researchers to position their research clearly. Thereby we provide a retrospective for the community and an entry point for new researchers to design empirical studies that embrace the human role in decision making.

 

Colloquium IS (November 3, 2017) – Interplay between learning and optimization

Dear all,

We are pleased to invite you to our next Colloquium IS that will take place on Friday,

November 3, 2017, 12:30 – 13:30 (Paviljoen K.16).

Speaker: Yingqian Zhang

Title: Interplay between learning and optimization

Abstract:

There are increasing interests in combining machine learning and optimization. In this talk, I will introduce two ongoing work in this research line.

In most existing approaches of using data to solve optimization problems, predictive (machine learning) models serve as decision variables, input parameters, or solution evaluation functions. In our work, we show how to use the internal structure of predictive models in optimization process, and demonstrate how the proposed approach helps to find better solutions.

Predictive models such as decision trees are typically built using sub-optimal algorithms, which often aim at optimizing loss functions (i.e., accuracy). These algorithms are not flexible when a different learning objective rather than accuracy is desired. We propose to transfer the decision tree learning problem to a mathematical optimization problem. In this way, different learning objectives, such as minimizing discrimination or false positive errors, can be easily specified for constructing optimal predictive models.

I will use online auction as an example to illustrate both approaches. 

 

Colloquium IS (October 6, 2017) – Leveraging linguistic modeling for clinical decision support

Dear all,

We are pleased to invite you to our next Colloquium IS that will take place on Friday,

October 6, 2017, 12:30 – 13:30 (Paviljoen K.16).

Speaker: Uzay Kaymak

Title: Leveraging linguistic modeling for clinical decision support

Abstract:
As electronic medical records become the norm for documenting medical history of patients, reuse of the data generated during the care process opens new ways of supporting clinical decisions. Advanced data analysis techniques, machine learning and data mining models that make secondary use of medical data are accepted more and more in clinical applications. Despite the advent of data-driven models, the practitioners find it important to have transparent models whose behavior can be understood well. In this respect, natural language is an effective means for communicating model behavior to the users. We argue that linguistic models based on fuzzy set theory form an excellent bridge between the data-driven modeling and the transparency required by the users in the clinical domain. In this presentation, we discuss data science challenges in the healthcare domain and consider several modeling approaches that use fuzzy set theory to develop models for supporting clinical decisions and improving the care process.

 

Micro to Macro in IS – at Which Level Should we Think ?

Dear all,

We are pleased to invite you to our next Colloquium IS that will take place on Friday,

September 1, 2017, 12:30 – 13:30 (Paviljoen K.16).

Speaker: Paul Grefen

Title: Micro to Macro in IS – At Which Level Should we Think?

Abstract:
IBM already contemplated the issue of aggregation levels (admittedly from a slightly different angle) a little while ago (actually, before some of us were born …): https://www.youtube.com/watch?v=0fKBhvDjuy0. This presentation applies this line of thinking to IS design (taking the world of MPMS as an example context) and intends to make you consider where your considerations are, or rather where your considerations should be.

Colloquium IS (July 7, 2017) – Compliance verification of inter-organizational workflows

Dear all,

We are pleased to invite you to our next Colloquium IS that will take place on Friday,

July 7, 2017, 12:30 – 13:30 (Paviljoen K.16).

Speaker: Pieter Kwantes

Title: Compliance verification of inter-organizational workflows

Abstract:
Inter-organizational workflows (IOW) are commonplace in industry. Often they are facilitated by an industry body for standardization of message formats, enabling electronic message exchanges between the participants of the IOW. The SWIFT organization, created in 1973 and responsible for maintaining message standards for the Financial services industry, is (to my knowledge) one of the first examples of such an industry body but there are many more (eg. HL7 for Healthcare, Rosetta in Electronics, EDSN for the Dutch energy market and so on). Making a design for an IOW and verifying its correctness is much more challenging than for an intra-organizational workflow and the stakes are higher. Ongoing research into this subject aims to find methods and tools to support this design and verification process. One question investigated in [1] is how to verify, using an automated procedure, that the design of a local workflow of an organization participating in an inter-organizational workflow is in compliance with the globally specified rules of that workflow. In this talk the results of [1] will be presented and future work will be discussed.

[1] Kwantes, P.M., Gorp, P.V., Kleijn, J., Rensink, A.: Towards compliance verification between global and local process models. In: Graph Transformation – 8th International Conference, ICGT 2015).

Bio:
Pieter Kwantes is a senior business consultant and project manager specialized in Investment Banking and holds a Master in Economics from the University of Amsterdam and a Master in Computer Science from the University of Leiden and is part-time Phd student also at the University of Leiden.