Grey Wolf optimization model for the best mean-variance based stock portfolio selection

Kriksciuniene, D., Sakalauskas, V., & Imbrazas, A. (2020, December). In International Conference on Innovations in Bio-Inspired Computing and Applications (pp. 120-130). Springer, Cham.

Viscovery SOMine is used to select a set of promising equities with high expected returns from S&P 500 data. Grey Wolf optimization is then used on these stocks to optimize the portfolio for minimal risk.

Trajectories of development of state-owned banks by analyzing the dynamics of patterns

Mussina, A., Shkolnyk, I. O., & Bukhtiarova, A. H. (2017).

The development of state-owned Ukrainian banks in the period from 2007 to 2016 is analyzed. Viscovery SOMine is used to cluster banks with respect to 14 indicators, describing their assets, deposits, capital and loans.

Financial performance analysis of European banks using a fuzzified self-organizing map

Sarlin, P., & Eklund, T. (2013). International Journal of Knowledge-Based and Intelligent Engineering Systems, 17(3), 223-234.

This paper conducts a financial performance analysis of European banks using PCA and self-organizing maps. Viscovery SOMine is used to cluster the performance data via the SOM-Ward algorithm. In a second step, a fuzzified Ward clustering is introduced on top of the map.

Segmentation in banking using self-organizing maps: a case study of business customers

Juković, S., Bach, M. P., Dumičić, K., & Šarlija, N. (2012, January). In 6th International Conference of the School of Economics and Business Beyond the Economic Crisis: Lessons Learned and Challenges Ahead.

The foundations of self-organizing maps and, in particular, of the SOM-Ward clustering algorithm, as introduced by Viscovery, are presented and demonstrated in an application for market segmentation. Viscovery SOMine is used to cluster a dataset of business clients of Croatian banks into three groups to derive relevant marketing activities.

Rating of enterprises' activities by the modified cluster method

Kravets, T., & Kuznetsov, G. (2011). Ekonomika, 90.

Rating of enterprises and their financial performance is the focus of this paper. For this purpose, Viscovery SOMine is used to obtain clusters of companies according to their revenue, paid taxes, labor costs and other performance indicators.

Artificial neural networks and self-organization for knowledge extraction

Aharkava, L. (2010).

This master thesis employs self-organizing maps and backpropagation neural networks to forecast financial time series data. Viscovery SOMine is used for visual-data analysis and for classifying Forex data into BUY and SELL recommendations.

Forecasting of credit classes with the self-organizing maps

Merkevičius, E., GarŔva, G., & Simutis, R. (2004). Information technology and control, 33(4).

The capabilities of self-organizing maps in forecasting of credit classes are investigated. Viscovery SOMine is used to generate a model of credit units with similar process characteristics to determine credit classes. It is shown that self-organizing maps may distinctly reduce misclassification errors.

Credit rating classification using self-organizing maps

Tan, R. P., van den Berg, J., & van den Bergh, W. M. (2002). In Neural Networks in Business: Techniques and Applications (pp. 140-153). IGI Global.

The aim of this article is to quantitatively reproduce the Standard and Poor (S&P) Ā ratings of 300 American companies trading in consumer cyclicals. Viscovery SOMine is used to cluster financial statement data, producing a good fit with S&P ratings and revealing that ratings are largely dependent on the financial indicators used.

European financial cross-border consolidation: at the crossroads in Europe? By exception, evolution or revolution?

Abraham, J. P., & Van Dijcke, P. (2002). SUERF Studies. (No. 22).

Cross-border financial consolidation is analyzed from the perspective of banking strategies. A sample of the 100 largest banking groups in Europe is selected on the basis of Bankscope data. Using Viscovery SOMine clustering, peer groups with similar characteristics are found.

An empirical evidence of the financial performance of lean production adoption: a self-organizing neural networks approach

Biscontri, R., & Park, K. (2000). In Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (Vol. 5, pp. 297-302). IEEE.

A feasibility study is performed to evaluate the application of self-organizing maps (SOMs) to examine the financial performance of US lean production firms. Using control-group design, the ability of SOMs to distinguish the financial performance between members of the target group (lean firm) and control group (non-lean firm) is tested. The investigated financial performance includes return on assets, current ratio, and the ratio of cost of goods sold to sale, gross profit ratio, asset turnover, and inventory turnover ratio. Results show that the SOM models successfully distinguish the financial performance of the lean firms from non-lean firms.

Credit rating prediction using self-organizing maps

Tan, R. P. G. H. (2000). Erasmus University Rotterdam.

The relationship between the financial statement of a company and its assigned credit rating is analyzed to show how much of a companyā€™s rating is affected by the qualitative analysis performed by the rating agency. Viscovery SOMine is used for credit-rating predictions, to visualize large datasets and gain novel insights.