Кафедри
Постійне посилання на розділhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/35393
Переглянути
2 результатів
Результати пошуку
Документ Improving the quality of credit activity by using scoring model(Запорізький національний технічний університет, 2019) Melnyk, K. V.; Borysova, N. V.Context. The problem of credit assessment of a client is considered. It is a simultaneous processing of lender’s data of different nature with further definition of the credit rating. The object of this study was the process of lending to individuals by credit institutions. Objective. The purpose of the work is to study the process of improving the quality of lending through the development and use of a scorecard model. Method. An analytical review of the domain area was conducted. A business process model for assessing clients’ creditworthiness in the form of an IDEF0 diagram is developed. Dedicated groups of indicators characterizing a potential lender from different directions. Selected sets of values for each indicator of credit separately. The methods of solving the problem of clients’ creditworthiness are analyzed. Selected Bayesian naive classifier as a method for solving the problem of classification of potential lenders. The existing information systems for assessing the creditworthiness of clients are analyzed. A scoring model for assessing credit ratings by the client in the form of an algorithm is developed. The list of functional requirements of the information system, which is presented in the form of a use case diagram is determined. Three-level architecture for the information system is proposed. A database model has been developed to preserve customer information. An information system was developed for determining the credit rating of a client based on the developed scoring model. Numerous studies have been conducted to determine the class of a potential creditor. The process of determining the quality of credit activity is analyzed. Quality indicators for assessing the creditworthiness of clients are selected. The method of calculating the quality of credit activity is offered. Results. The scoring model was developed, which was used in solving the credit assessment of clients through the help of the proposed information system. The process of improving the quality of credit rating is investigated. Conclusions. The conducted experiments have confirmed the proposed scoring model and allow recommending it for use in practice for assessment process of client creditworthiness. Scientific novelty is to improve the process of credit activity by automating the use of naïve Bayes classifier, which reduces the human factor in decision-making.Документ Efficiency estimation of methods for sentiment analysis of social network messages(Національний технічний університет "Харківський політехнічний інститут", 2019) Borysova, N. V.; Melnyk, K. V.The results of effectiveness evaluating of machine learning methods for sentiment analysis of social network messages are presented in this paper. The importance of the sentiment analysis problem as one of the important tasks of natural language processing in general and text ual information processing in particular is substantiated. A review of existing methods and software for sentiment analysis are ma de. The choice of classifiers for sentiment analysis of texts for this research is substantiated. The principles of functioning of a Naïve Bayesian Classifier and classifier based on a recurrent neural network are described. Classifiers were sequentially trained in two corpuses: first, in the RuTweetCorp corpus, the corpus of short messages from the social network Twitter, and then on the Slang corpus, the corpus of messages from social networks Facebook and Instagram and posts from the Pikabu website, second corpus have been marked up the tonality of slang words. Information about the tonality of slang words was taken from the youth slang dictionary obtained as a result of the survey of users. The separation of texts by tonality was carried out into three c lasses: positive, negative and neutral. The efficiency of these classifiers was evaluated. Efficiency evaluation was carried out according to standard metrics Recall, Precision, F-measure, Accuracy. For the naive Bayesian classifier, after training on the first corpus, the following metric values were obtained: Recall = 0,853; Precision = 0,869; F-measure = 0,861; Accuracy = 0,855; and after training on the second corpus such values were obtained: Recall = 0,948; Precision = 0,975; F-measure = 0,961; Accuracy = 0,960. For the classifier based on a recurrent neural network, after training on the first corpus, the following metric values were obtained: Recall = 0,870; Precision = 0,878; F-measure = 0,874; Accuracy = 0,861; and after training on the second corpus such values were obtained: Recall = 0,965; Precision = 0,982; F-measure = 0,973; Accuracy = 0,973. These results prove that additional training on the second corpus increased the efficiency of classifiers by 10–11%.