AGRICULTURAL INVESTMENT RATING MODEL

FOR ENTERPRISE BASED ON FUZZY CLUSTERING

Gromov V. V., graduate student of chair «Applied Mathematics Department», Computer Technologies and Applied Mathematics faculty, the Kuban State University, Krasnodar, Russia

It is necessary to classify Investment Rating of Agricultural companies especially in Krasnodar region. Agricultural complex is a priority in the development of the Krasnodar region economy.

We suggest a model based on Fuzzy Logic which can work with minimal data to give more accurate Investment ratings. Preliminary analysis of the model outputs confirms the advantages of the Fuzzy Logic model over the current models.

Many of the current scoring models use the Altman Model in some form or the other. This model while being simple to use, has problems relating to the availability of data and multi-collinearity of variables.

The design of the Fuzzy Logic Investment Rating System involves the following steps:

1) We selected the data of 150 Agricultural companies. We used balance sheet and profit-and-loss report.

2) The following 4 groups are selected as input parameters:

- liquidity;

- profitability;

- business activity;

- financial soundness.

For each company were counted 15 ratios. And for each ratio were built clustering histogram (Picture 1).

Picture 1 - Clustering histogram for each ratio

Next steps:

3) We have identified five fuzzy classes: very low level of factor (OH) - Low levels of factor (H) - Medium factor (CP) - High levels of factor (B) - very high level of factor (ОВ).

4)

Fuzzy logic model (mamdani)

Building fuzzy logic system (Picture 2).

View rules

Surface of fuzzy model

Editor rules

Membership functions (mamdani)

Picture 2 - Building fuzzy logic system

Conclusion

Fuzzy systems have found practical application in many cases. The model developed here, with only financial parameters as inputs, gave results which were more accurate than models based on Multi Discriminant analysis, such as the Altman model. This shows that Fuzzy Logic models have an inherent advantage because of their ability to take care of the fuzziness or ambiguity in the system. Other advantages include easy interpretability and scope for integration with other systems such as neural networks for higher accuracy.

Further, Fuzzy Logic models can be integrated with neural networks resulting in a better model with higher prediction accuracy to make the model self-learning. The scope of the model increases when one incorporates qualitative data the system.

References

1. Gromov V. V. Rating agricultural enterprises of Krasnodar Territory / Applied Mathematics XXI century (Intrahigh collection), materials X Joint Scientific Conference of students and graduate students of computer technology and applied mathematics faculty. Krasnodar: Kuban State University, 2011.

2. Ognev Y. Y. Аgrarian question. The main proposals / Y. Y. Ognev. M: Press, 2010. 56 p.