Designing Collaterals Assessment Model to Finance Technological Projects and SMEs by Adaptive Neural Fuzzy Inference System (ANFIS)

Financing is one of the factors of future success for small and medium-sized technology businesses. Because of the immaturity of these businesses, the majority of their assets are intangible, rely on technical knowledge, and lack significant financial and credit records. To control the probable risks, financing systems traditionally rely on patterns based on maximum authentication of physical assets, which do not fulfill the needs of these firms and must be altered. The fundamental purpose of this research is to create a model for assessing and determining the collaterals of technical projects and knowledge-based firms so that finances could be more easily obtained and the risk of non-refunding could be managed. In this research, in the first step, the criteria for evaluating and assessing the intended project and company were defined. By using a fuzzy expert system, the appropriate method of dealing with companies was determined. In the second step, in order to create a learning system, the results of the first step were used as input data in the form of three neural network algorithms implemented in MATLAB software and ANFIS algorithm, with 93% accuracy compared to the input data.

The final neuro-fuzzy model was tested according to the repayment data available in Iran National Innovation Fund. The statistical population included knowledge-based firms receiving facilities. By using The Cochran formula, 103 companies were selected as a sample. The results obtained by testing and evaluating the model, in 85% of cases, could correctly identify the companies' performance in repaying resources and suggest appropriate collateral (Real estate collateral or Bank Guarantees).

The model presented in this study can be used to evaluate, validate, and determine the collaterals of technological projects and knowledge-based firms. It can facilitate their access to financial resources and also help them with managing the attendant risks. It also employs new optimization methods and has the ability to learn.