An integrated two-stage methodology for optimising the accuracy of performance classification models

Technological and Economic Development of Economy

Massimiliano Ferrara¹  Florentin Şerban²  Adrian Costea³ 

[1] CRIOS – Centre for Research on Innovation, Organization and Strategy, Department of Management and Technology, Bocconi University and Department of Law and Economics, University Mediterraneaof Reggio Calabria, Via dei Bianchi, 2 – Palazzo Zani – 89127 Reggio Calabria, Italy;Department of Applied Mathematics, Faculty of Cybernetics, Statistics and Informatics in Economy, Bucharest University of Economic Studies, 15-17 Calea Dorobanti St., “Ion Angelescu” Building, 6th Floor, Room 2625, Sector 1, Bucharest, Romania, 010552;Department of Statistics and Econometrics and Data Mining Group Laboratory, Faculty of Cybernetics, Statistics and Informatics in Economy, Bucharest University of Economic Studies, 15-17 Calea Dorobanti St., “Ion Angelescu” Building, 6th Floor, Room 6207, Sector 1, Bucharest, Romania, 010552;

关键词: knowledge-based systems;    uncertainty modelling;    applications of fuzzy sets;    classification;    artificial intelligence;    performance evaluation;   

DOI  :  10.3846/20294913.2016.1213196

来源: DOAJ

【 摘 要 】

In this paper we propose a two-stage methodology to classify the non-banking financial institutions (NFIs) based on their financial performance. The first stage of the methodology consists of grouping the companies in similar financial performance classes (e.g.: “good”, “average”, “poor” performance classes). We optimise the allocation of the observations within the performance clusters by applying an enhanced version of an observation re-allocation procedure proposed in our previous work. Next, based on the result of the grouping phase, we construct a performance class variable by attaching a performance label to each data row. Then, in the second phase of our methodology, we propose a feed-forward neural-network classification model that maps the input space to the newly-constructed performance class variable. This model allows us to forecast the performance of new companies as data become available.

【 授权许可】

Unknown