This paper presents a new clustering technique based on Ex-treme Learning Machine (ELM). This clustering technique can incorpo-rate a priori knowledge (of an expert) to define the optimal structure of the clustering; for example, the number of points in each cluster. Using ELM, the clustering can be rewritten as a Traveling Salesman Problem and solved by a Genetic Algorithm. This efficient and fast clustering technique is used in order to analyze and predict financial distress of French companies.
|Title of host publication||International work-conference on Time Series (ITISE)|
|Publication status||Published - 2014|
|MoE publication type||A4 Article in conference proceedings|
- 512 Business and Management
Akusok, A., Veganzones, D., Björk, K-M., Séverin, E., du Jardin, P., Lendasse, A., & Miche, Y. (2014). ELM Clustering – Application to Bankruptcy Prediction. In International work-conference on Time Series (ITISE)