The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
The establishment financial crisis early warning system has the very vital significance to national economy's construction, the financial crisis is a complex non-linear problem, the present model is based on the linear method, but the neural network is suitable to the processing non-linear problem. This paper improves the BP algorithm with the simulation annealing algorithm, effectively overcomes...
The paper studies the application of principal component analysis and ANN (Artificial Neural Networks) for pre-warning of enterprise financial crisis, analyzes the factors of financial crisis, and constructs the model of the enterprise financial crisis with principal component analysis and ANN. It integrates simplifying of enterprise financial crisis index, dynamic learning of financial crisis knowledge...
Since correct prediction of bankruptcy prediction of a company is very important for investors, lenders and managers, most efforts have been done to improve the predictive capability of corporate bankruptcy prediction models. Most previous studies use corporate financial statement to do bankruptcy prediction. However, corporate performance is always affected by macroeconomic conditions. This study...
This paper designs a enterprise informatization index system from the areas of finance, business process, customer service and strategy and development, based on Balanced Score Card (BSC) theory. A model based on back propagation neural network is established for evaluating the level of enterprise informatization performance. Eventually, we apply the new model to real cases to prove its good precision...
In this paper, we studied the two most commonly used artificial intelligence methods (Multilayer Perceptron and Radial Basis Function network) to build the credit scoring model of applications, and analyzed the most important restraining factors of the applications of neural network which is the exponential increase in the variables bringing the model over-complex. On this basis, the author combines...
With the economic development of the emerging market countries, bankruptcy and financial crisis occur more and more frequently in business, credit and savings institutions, and thus the demand for enterprise financial crisis prewarning is rapidly growing. The main purpose of this paper to build a business financial crisis prewarning model based on BP neural network to conduct empirical analysis of...
This paper use Microsoft SQL Server 2005 data mining tools and three methods of neural networks, decision trees and logistic regression to establish the financial crisis early-warning model of listed companies. The conclusion is that the three kinds of methods have good results and the prediction accuracy rate are 80% or more. The accuracy of the decision tree algorithm model is higher than others.
Government, business and financial systems all have an impact on capacity of independent innovation. Accordingly, build a Multi-element Funding model and test model's validity. Use artificial neural network model to evaluate and predicate the capability of independent innovation. It should consolidate the dominant position of enterprise independent innovation, strengthening the government's guiding...
Time series forecasting is useful in many researches areas. The use of models that provide a reliable prediction in financial time series may bring valuable profits for the investors. This paper proposes a methodology based on information obtained from exogenous series used in combination with neural networks to predict stock series. The best trained neural networks were used in combination to improve...
Traditional method of tender offer is subjective and arbitrary, and the ARIMA Accuracy can't satisfy the tenderer. We have combined the Elman NN with the SVM model to establish a new hybrid optimization algorithm, which are presented to the bidding tender offer in a project. Experimental results show that agents adopting the strategy outperform agents using other strategies reported in the literature...
The guiding principle of process automation and soft computing is to achieve more robust, traceable and low cost solutions which incorporate the required intelligence to information technologies, thus enabling human centered functionalities. The application of Artificial Intelligence (IA) and Neural systems to the financial and banking industries has performed well in the areas of Risk Management...
In this paper, using factor analysis to study the sources of China's financial risk, concluded that the major factor of the financial risks is macroeconomic risk, foreign investment risk, banking risk and the stock market risk; using BP artificial neural network model for the establishment of early warning and training and testing the sample data with it, and then prediction the state of the financial...
Credit Risk Identification in small and medium enterprises(SMEs) is a real problem which is necessary to be solved in financial sector. Focusing on 32 small and medium enterprises which had bank loan, dimension of six indicators used to judge whether enterprises had credit risk was reduced to simplify model by adopting the factor analysis method. Then small sample data was trained and simulated in...
This article aims to analyze the problems of housing mortgage loans. And it establishes an index system of credit risk evaluation according to the differences between developers and lenders. Based on artificial neural network, it establishes a credit risk evaluation and forecast model in housing mortgage loans, which will lay a foundation for the change of credit risk evaluation pattern and for the...
The comprehensive evaluation problem of electric power listed corporation has always been a focus since market-oriented reform of the electric power industry, and financial risk evaluation play a key role to science investment decision of electric power listed corporation .This paper presents a new composite forecasting method for financial risk of electric power corporation, modeling and forecasting...
Forecasting exchange rate is an important financial problem that is received much more attentions because of its difficulty and practical applications. The problem of prediction of foreign exchange rates by using multi expression programming and immune programming based flexible neural tree (MEPIP-FNT) is presented in this paper. This work is an extension of our previously traditional FNT model which...
The result of value appraisal decides whether an enterprise acquires target or not. Discounted cash flow is a theoretical, widely applied method of value appraisal. However, there are flaws of the theory in predicting cash flow by linear model, static appraisal and ignoring integration cost. This paper tries to amend the flaws in predicting cash flow by genetic neural network, combining games and...
Research on stock company comprehensive assessment has always been an important focus for economists and computer experts. In this paper, the financial indexes reflecting the comprehensive capability of stock companies as main research objects including income per thigh, clean asset per thigh, profit rate of clean asset, Kohonen network with the advantage of clustering is applied to assess for stock...
This study aims at the basis of patent law and proposes an integrated evaluator constructed by a revolutionary evaluation model. Regardless of stock performance or revenue generated by the enterprise, the damage award of a patent infringement lawsuit is deemed to be a legal value of a patent in view of the patent law. Effective samples are extracted from 4,289 patent infringement lawsuits retrieved...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.