Difference between revisions of "STSM"
Jump to navigation
Jump to search
| Line 26: | Line 26: | ||
* Supervisor at ZHAW, Switzerland: [https://www.zhaw.ch/en/about-us/person/hadj/ Dr. Branka Hadji Misheva], Scientific Employee, Zurich University of Applied Sciences] | * Supervisor at ZHAW, Switzerland: [https://www.zhaw.ch/en/about-us/person/hadj/ Dr. Branka Hadji Misheva], Scientific Employee, Zurich University of Applied Sciences] | ||
| − | * Supervisor at UCM, Spain: [https://www.linkedin.com/in/javier-arroyo-gallardo-390aa019b/ | + | * Supervisor at UCM, Spain: [https://www.linkedin.com/in/javier-arroyo-gallardo-390aa019b/ Prof. Dr. Javier Arroyo], MC Member and Associate Professor at [https://informatica.ucm.es/ Facultad de Informática], [https://www.ucm.es Universidad Complutense de Madrid] |
* STSM project: In this project, in the working group 2 - Transparent versus Black Box Decision-Support Models in the Financial Industry [https://fin-ai.eu/index.php/wg2-transparent-versus-black-box-decision-support-models-in-the-financial-industry/], we will investigate the tradeoff between explainability and predictive performance of different black-box models as they apply to financial problem sets, primarily in risk management-credit risk. Specifically, we will study the elements that must be evaluated for a black-box model to be considered interpretable and explainable to take advantage of its predictive potential. | * STSM project: In this project, in the working group 2 - Transparent versus Black Box Decision-Support Models in the Financial Industry [https://fin-ai.eu/index.php/wg2-transparent-versus-black-box-decision-support-models-in-the-financial-industry/], we will investigate the tradeoff between explainability and predictive performance of different black-box models as they apply to financial problem sets, primarily in risk management-credit risk. Specifically, we will study the elements that must be evaluated for a black-box model to be considered interpretable and explainable to take advantage of its predictive potential. | ||
Revision as of 18:48, 4 January 2021
Short-term scientific missions support our COST Action.
If you want to apply, please see here.
Applications Grant Period 1
If you are an evaluator for the STSM and ITC conference grant applications, you can find them here (protected).
Ahmad Amine Loutfi, PhD Fellow, Norwegian University of Science and Technology (NTNU), Norway.[1]
- Host institution: Institute of Wealth & Asset Management, Zurich University of Applied Sciences (ZHAW), Switzerland.
- Supervisor at ZHAW, Switzerland: Prof. Dr. Peter Schwendner, Director of Institute[2]
- Supervisor at NTNU, Norway: Prof. Dr. Per Bjarte Solibakke.[3]
- STSM project: In this project, we propose to study the extent to which alternative data (News/reports) can predict electricity spot prices. This will allow us to assess the backtesting of relevant investment strategies. The results of this project will also be used to extend an ongoing research project where we study electricity spot price prediction based only on conventional data. We aim to augment the conventional data set with a new feature which reflects the alternative data, and then run the newly augmented dataset through the same neural network model and then compute the new loss function results in order to assess the models’ performance with and without alternative data.
Miller Janny Ariza Garzón, PhD student at Data Science [4].Research member of Project FINTECH-EU Ho2020 [5]. Facultad de Informática [6]. Universidad Complutense de Madrid (UCM) [7]. Spain.
- STSM title: Fintech and Artificial Intelligence in Finance - Towards a transparent financial industry (FinAI).
- Host institution: Zurich University of Applied Sciences (ZHAW) School of Engineering, Winterthur, Switzerland.
- Home institution: Universidad Complutense de Madrid (UCM), Madrid, ES.
- Supervisor at ZHAW, Switzerland: Dr. Branka Hadji Misheva, Scientific Employee, Zurich University of Applied Sciences]
- Supervisor at UCM, Spain: Prof. Dr. Javier Arroyo, MC Member and Associate Professor at Facultad de Informática, Universidad Complutense de Madrid
- STSM project: In this project, in the working group 2 - Transparent versus Black Box Decision-Support Models in the Financial Industry [8], we will investigate the tradeoff between explainability and predictive performance of different black-box models as they apply to financial problem sets, primarily in risk management-credit risk. Specifically, we will study the elements that must be evaluated for a black-box model to be considered interpretable and explainable to take advantage of its predictive potential.