Yazar "Atagün, E." seçeneğine göre listele
Listeleniyor 1 - 4 / 4
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Effective Factor Detection in Crowdfunding Systems(Springer Science and Business Media Deutschland GmbH, 2021) Atagün, E.; Karagül Yıldız, T.; Timuçin, T.; Gündüz, H.; Bayıroğlu, H.Crowdfunding is a platform that brings together entrepreneurs without their own budgets and investors who do not have to be related to each other. Crowdfunding, a model that enables the entrepreneurs to get the support they need to realize their projects, is increasingly used in the world and in our country as well. This study aims to open new horizons for entrepreneurs about what they should pay attention to get support for their projects. The crowdfunding system is important to prevent wasting of potential projects that may be beneficial to the society when they are implemented due to lack of resources. The fact that the project is not expressed in a way that attracts the attention of investors makes it difficult to use the system effectively. Our study answers the question of how to use this system more effectively by applying machine learning methods on a public data set. Also, the outcome of the study is expected to benefit both entrepreneurs and investors. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Effectiveness of Genetic Algorithm in the Solution of Multidisciplinary Conference Scheduling Problem(Springer Science and Business Media Deutschland GmbH, 2021) Atagün, E.; Biroğul, S.Multidisciplinary conferences are the types of conferences that allow the presentation of studies in different disciplines such as naturel science, social sciences, health and arts sciences etc. In these conferences, determining the days, halls and sessions and making presentations according to the related main-scope and sub-scopes, are an important limited optimization problem. The fact that there are presentations from different disciplines in same session during the conference is a big problem for the conference participants. In this study, the solution of the scheduling problem of multidisciplinary conferences with Genetic Algorithm approach is discussed. The basic concepts of Genetic Algorithm are given and conference scheduling schemes and the elements to be considered in scheduling are indicated. In this study, two different multidisciplinary conference datasets have been used. An application has been developed with Genetic Algorithm in C# language under some constraints of the different days, different sessions and different rooms. As a result of the study, it is seen that the solutions obtained with Genetic Algorithm are generally close to optimum solutions. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Predictive Analysis of the Cryptocurrencies’ Movement Direction Using Machine Learning Methods(Springer Science and Business Media Deutschland GmbH, 2021) Timuçin, T.; Bayiroğlu, H.; Gündüz, H.; Yildiz, T. K.; Atagün, E.Cryptocurrencies are among the most interesting financial instruments of recent years. Unlike the classical understanding that money exists as a means of change from one hand to another, this digital economy has begun to attract people's attention. The most popular currency emerging from this concept of cryptocurrency is “Bitcoin”. As the popularity of Bitcoin started to increase since 2016, the number of academic studies on cryptocurrencies has increased in parallel. In light of these developments, our study proposes predictive models of price change directions of high market value cryptocurrencies. Bitcoin, Ethereum and Litecoin were selected as cryptocurrencies and daily opening, closing, high and low prices of these currencies were collected from financial websites. Preprocessing was performed on the collected data to create input vectors. These vectors were given regression algorithms which are Multiple Linear, Polynomial, Support Vector, Decision Tree and Random Forest Regression. As evaluation metrics, R-square Method (R2) and Root Mean Square Error (RMSE) were chosen. After doing experiments with different parameter settings, it was found out that the chosen machine learning models showed satisfactory performances in predicting the directions of then mentioned cryptocurrencies. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Text Mining Based Decision Making Process in Kickstarter Platform(Springer Science and Business Media Deutschland GmbH, 2021) Yildiz, T. K.; Atagün, E.; Bayiroğlu, H.; Timuçin, T.; Gündüz, H.Kickstarter is a platform that supports the transformation of projects into products by embracing entrepreneurial investor interaction. Entrepreneurs who register on the Kickstarter website exhibit presentations and visuals on their projects. People who work or have new ideas in the fields of art, comics, design, technology, film, games, music and publishing are looking for support to improve their ideas. Entrepreneurs display the project details in a textual expression in order to attract investors’ interest. Investors make a decision to invest in the project by reading these expressions and consider them logically. Investors need to solve the difficulties they encountered in decision-making through various artificial intelligence or language processing methods. Natural Language Processing (NLP) is one of the preferred methods for such decision-making problems. In this study, NLP techniques and word attributes were obtained from the explanations of the projects in order to provide support to the investors. In addition, temporal attributes were extracted by considering the start and end times of the projects. According to these attributes, whether the projects can reach the targeted budget has been determined by artificial learning methods and predictable effects of some words or phrases in reaching the targeted budget have been highlighted. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.
