Neural network application to perception of local risk
Başlık çevirisi mevcut değil.
- Tez No: 364544
- Danışmanlar: PROF. DR. AYTÜL ERÇİL
- Tez Türü: Yüksek Lisans
- Konular: İşletme, Business Administration
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 1997
- Dil: İngilizce
- Üniversite: Boğaziçi Üniversitesi
- Enstitü: Sosyal Bilimler Enstitüsü
- Ana Bilim Dalı: İşletme Ana Bilim Dalı
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: Belirtilmemiş.
Özet
Özet yok.
Özet (Çeviri)
If the markets are efficient, no other portfolio should consistently outperform is the performance of according to Markowitz model optimized portfolios. The starting point of this research is the observation that some traders consistently make superior profits. Knowing that insiders and manipulators are rare cases, we draw our attention to what dealers name as a 'feeling'. The expression that they 'feel' is true because they do not use explicit deterministic rules for calculation of expectations about risk&return. Human brain implicitly learns concepts and rules. Our aim in this paper is to isolate one such 'feel' or method to show their existence and usefulness in portfolio management techniques. As a target for our research, we selected the concept of dynamic local risk perception. One of the rriathematical structures that learn through experience withom specifying explicit rules, is the neural network (NN) structure. From various possible NN types we used back-propagation NN to measure and document this 'feeling', because they are the most widely used networks and the theory of them are the most complete one. We worked on <;ukurova and Eregli stocks and attained reasonable correlations for predicting risky and normal days. This 'feeling' is one of the most simplistic concepts that traders use, which can't be explicitly defined but can be mimicked by NN. We believe that NN's can be used to explain many such rules that can't be explicitly defined but are of great advantage to portfolio managers.
Benzer Tezler
- Derin öğrenme destekli dielektrik rezonatör anten tasarımı
Deep learning assisted dielectric resonator antenna design
FİDAN GAMZE KIZILÇAY
- U-net architecture optimization for optic disc segmentation in retinal images
Retina görüntülerinde optik disk bölütleme için U-net mimarisi optimizasyonu
ZAFER ERDOĞAN
Yüksek Lisans
İngilizce
2019
İstanbul Teknik ÜniversitesiBilgisayar Mühendisliği Ana Bilim Dalı
Yükleniyor...
- Genomik verilerin prostat kanseri sürecindeki etkisinin incelenmesi
Examining the impact of genomic data on the prostate cancer process
AHMET DEMİRÖZ
- İmalat sistemlerinin tasarlanması ve öncelik kurallarının belirlenmesinde yapay sinir ağlarının kullanılması
<the use of neural networks in determination of the manufacturing systems design and dispatching rules
TARIK ÇAKAR
- Bulanık bilişsel haritalama metodu kullanılarak Kayseri-Engir Sazlığı'nın sorunlarının ve potansiyellerinin değerlendirilmesi
The evaluation of the problems and potentials in Enger Marshes by using the fuzzy cognitive mapping technique
PERVİN TAŞKIRAN TIRPAN
