Emre Kesici

Emre Kesici

Auto-generated profile, based on publicly available information

Emre Kesici

Secure AI & Autonomy Laboratory, University of Texas at San Antonio, San Antonio, TX 78249, USA and Department of Finance, University of Texas at San Antonio, San Antonio, TX 78249, USA

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 May 2020 in IEEE Access
Verified
Journal Article
Open access
HCHenry Chacon
Henry Chacon
EKEmre Kesici
Emre Kesici
PNPeyman Najafirad
Peyman Najafirad
Recurrent neural networks have received vast amount of attention in time series prediction due to their flexibility in capturing dependencies on various scales. However, as in most of the classical forecasting methods, its accuracy is strongly tied to the degree of signal complexity. Specifically, stock market prices are commonly classified to be non-linear, non-stationary and chaotic signals, since they exhibit erratic behavior that conducts a poor performance in the long short-term memory (LSTM). In this paper, we propose a methodology to improve the predictability of financial time series by using the complete ensemble empirical mode decomposition with adaptive noise and the intrinsic sample entropy (SampEn). We evaluated the integrated model by applying it to S&P 500 index stocks for the period between January 2018 and April 2020 and for each time series of stock closing prices, an LSTM model was trained to forecast the next closing price. The experimental results represent a dependency between the decomposed signal entropy and the performance of forecast accuracy. This suggests that in those cases where the short-term complexity in financial time series is smaller compared to the series energy, the forecasting capabilities are significantly improved after the removal of decomposed highest frequency. Furthermore, our results show an improvement in forecasting the direction of the stock price by 31% using the classical LSTM architecture.

1 January 2014 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
EKEmre Kesici
Emre Kesici
Turkish Borsalar ve teşkilatlanmış piyasalarda içsel bilgileri kullanarak menfaat elde edilmesi her zaman sermaye piyasalarıyla ilgili olarak ilgi çekici konu olmuştur. İçerden öğrenenlerin ticareti suçu kısaca kamuya açıklanmamış bilgileri kullanılarak halka açık şirketlerin paylarında işlem yapılması olarak tanımlanabilir. Her ne kadar bilgi suistimali suçu Türkiye'de yeni bir konu olsa da, bu suça ilişkin kayıtlar, suçun en azından 18. yüzyılın başına kadar uzandığını göstermektedir. Bilgi suistimali suçunu engellemeye yönelik tasarlanan kurallar ve düzenlemeler, temel olarak sermaye piyasalarının güvenli, şeffaf, etkin, istikrarlı, adil ve rekabetçi bir ortamda gelişmesini ve işlemesini temin etmek amacını taşımaktadır. Bilgi suistimali niteliğindeki işlemlerin engellenmesi ve söz konusu nitelikte işlem gerçekleştirenlere yaptırım uygulanması konusunda borsalar ve düzenleyici otoriteler arasında belirli ölçülerde işbirliği bulunmaktadır. Görev paylaşımının derecesi ülkeden ülkeye değişmekte, fakat genel olarak gözetim faaliyetlerinin öz düzenleyici kuruluşlar tarafından yürütüldüğü, denetim faaliyetlerinin ise düzenleyici otoritelerin görevi olduğu görülmektedir. Mevcut durumda, bilgi suistimali suçunun engellenmesi amacıyla SPK ve Borsa İstanbul düzenlemelerinde birçok araç bulunmaktadır. Bu düzenlemelere ilave olarak, 30.12.2012 tarihinde yürürlüğe giren 6362 sayılı Sermaye Piyasası Kanunu’nu yeni hükümler içermektedir. Bu çerçevede, 6362 sayılı Sermaye Piyasası Kanunu’na dayanılarak, Piyasa Bozucu Eylemler Tebliği, Bilgi Suistimali ve Piyasa Dolandırıcılığı İncelemelerinde Uygulanacak Tedbirler Tebliği, Bildirim Yükümlülüğü Tebliği ve Yöneticilerin Net Alım Satım Kazançlarını İhraççılara Ödemeleri Hakkında Tebliği hazırlanmış ve yayımlanmıştır. English Purchase and sale of securities depending on inside information has always been a attractive issue regarding capital markets. Insider trading can be shortly described as the trading of a public company' securities by individuals with access to non-public information about the company. Although the insider trading is relatively new issue in Turkey, the records show that history of insider trading dates at least back to the beginning of 18th century. Rules and regulations designed to prevent insider trading basically aim to ensure the functioning and development of capital markets in a secure, transparent, efficient, stable, fair and competitive environment and to protect the rights and interests of investors. A certain degree of cooperation exists between the regulatory authorities and exchanges in preventing insider trading acts and imposing sanctions on wrongdoers. The degree of cooperation is subject to differ among countries; however, it is generally observed that surveillance activities are carried out by the self regulatory organizations, whilst enforcement activities are the duties of the regulatory organization. Currently, there are several tools available in the Capital Markets Board of Turkey and Borsa Istanbul regulations to prevent insider trading. Addition to those regulations, the Capital Markets Law no. 6362 dated 30/12/2012 consist new provisions. In this context, based on the Capital Markets Law no. 6362, the new communiqués named; Communiqué on Market Abuse, Communiqué on Measures of Insider Trading and Manipulation, Communiqué on Obligation of Notification and Communiqué on Payment of Net Trading Earnings By Executives of Issuers to Issuers, have been prepared and issued.