Статьи журнала - International Journal of Modern Education and Computer Science
Все статьи: 1064
Credit risk prediction using artificial neural network algorithm
Статья научная
Artificial neural network is an information processing system which is influenced by the human brain and works on the same principles of the biological nervous system. They possess the ability to extract meaning from complex and intricate data, by detecting trends and extracting patterns from it. This paper illustrates the ability of neural network model and linear regression model constructed to predict the creditworthiness of an application accurately and precisely with minimal false predictions and errors. The results are shown to be similar for both the models, thus, models are efficient to use depending on the type of application and attributes.
Бесплатно
Criterion for Ranking Interval Alternatives in a Decision-Making Task
Статья научная
The study solves the problem of improving the methodological and algorithmic support of the decision-making process by developing a model of the preference criterion for interval evaluations of alternatives. The aim of the study is to improve the efficiency of decision-making based on interval expert data under conditions of uncertainty and risk by developing a criterion for the preferences of interval evaluations of overlapping alternatives. The object of the study is the decision-making process based on the classical efficiency matrix with interval elements, the subject is the model of decision maker's (DMP) preference criteria for interval evaluations of alternatives. The relevance of the task is stipulated by the urgency of the problem of adapting classical decision-making methods and models to practical problems of gray analysis, in particular, with interval uncertainty of primary expert data. A multifactorial model of the normalized preference criterion for interval evaluations of alternatives is proposed. Due to the additional consideration of the degree of preference of the DMP for the width of interval estimates, it allows ranking interval estimates of alternatives that overlap and are considered classically incomparable. A single analytical form of the normalized criterion model for ranking interval, weighted interval and point estimates makes it possible to increase the degree of automation of processing interval expert estimates in the decision-making process. Recommendations for the practical application of the proposed model are formulated. The developed model and corresponding algorithms can be used in automated expert decision support systems.
Бесплатно
Critical Analysis of Data Mining Techniques on Medical Data
Статья научная
The use of Data mining techniques on medical data is dramatically soar for determining helpful things which are used in decision making and identification. The most extensive data mining techniques which are used in healthcare domain are, classification, clustering, regression, association rule mining, classification and regression tree (CART). The suitable use of data mining algorithm can enhance the quality of prediction, diagnosis and disease classification. Valuation of data mining techniques demand for medical data mining is the major goal here, particularly to examine the local frequent disease like heart ailments, breast cancer, lung cancer and so on. We examine for discovering the locally frequent patterns through data mining technique in terms of cost performance speed and accuracy.
Бесплатно
