Surveillance of complex auction markets: A market policy analytics approach
Başlık çevirisi mevcut değil.
- Tez No: 539871
- Danışmanlar: Prof. Dr. W. KETTER
- Tez Türü: Doktora
- Konular: Ekonomi, İşletme, Economics, Business Administration
- Anahtar Kelimeler: Belirtilmemiş.
- Yıl: 2018
- Dil: İngilizce
- Üniversite: Erasmus Universiteit Rotterdam
- Enstitü: Yurtdışı Enstitü
- Ana Bilim Dalı: Belirtilmemiş.
- Bilim Dalı: Belirtilmemiş.
- Sayfa Sayısı: 222
Özet
Özet yok.
Özet (Çeviri)
As technology advances, the past two decades have seen an explosion of digital data and every sector of the global economy is being changed by the large amount of data available. This has enabled a different way of making decisions that involves more empirical evidence rather than personal experience, intuition, or belief. In this thesis we focus on the merits of using data analytics for decision making in complex auction markets from the perspective of policy-makers. More specifically we propose a Data-Driven Market Surveillance Framework enabling Market Surveillance Committees to establish recommendations or assessments by processing information from relevant data using appropriate tools to make important inferences and discover useful insights. In first study (Chapter 3) we examine the fractal dynamics of spot market prices by using parametric and semiparametric approaches in a multi-time tariff setting. We find that that prices have long-term correlation structure for the first and third time zones indicating that marginal bidders bid hyperbolically and not at their marginal costs, market is not weak form efficient at these hours and exogenous shocks to change the mean level of prices will have permanent effect and be effective. On the other hand, for the second time zone we find that price series does not exhibit long-term memory. This finding suggests the weak form efficiency of the auction in these hours and that marginal bidders bid at their marginal costs. Furthermore this indicates that exogenous shocks will have temporary effect on prices in these hours. These findings constitute an important foundation for MSCs to understand level of market efficiency for specific trading periods, develop appropriate monitoring indexes and conduct ex-ante impact assessment. In the second study (Chapter 4) we address three key forecasting challenges; risk of selection of an inadequate forecasting method and transparency level of the market (availability level of public data) and market-specific multi-seasonality factors in complex auction markets; and reveal the key distinguishing features of this auction quantitatively which then allow us to propose individual and ensemble forecasting models that are particularly well suited to it. We find that using ensemble forecasts can be useful to manage market price modelling risk in semi-transparent market settings. In the third study (Chapter 5), we demonstrate how attitude and trading behaviour of bidders effect their price expectations in complex auction markets with the existence of forward trading. We develop a research model that empirically tests the impact of bidders' attitudes on their price expectation through their trading behaviour. Using a unique and extensive data set, we tested our hypotheses on real ex-ante forecasts, evaluated ex-post. This study is the first to take an information-based view to investigate price expectation of bidders through their behaviour; with results that suggest a re-consideration of some of the conventional concepts. In the fourth study (Chapter 6), we investigate characterization, determinants, and efficiency of bidding in an oligopolistic multi-unit auction. We find that there is significant heterogeneity across bidders in terms of bidding behaviour. Through introducing novel classification variables, we identify five distinct bidding strategies. Then we demonstrate bidder's choice of these strategies is associated with their forward commitment, size, generation technology, and diversity. In addition, we show that different strategies, in aggregate, lead to different winning likelihoods and productive efficiency. Finally, we demonstrate how our analysis approach and findings can be used to enhance behavioural monitoring of Market Surveillance Committees. Overall, we have illustrated the merits of data analytics to improve the operations of Market Surveillance Committees in complex auction markets.
Benzer Tezler
- An examination of financial regionalism in East Asia through new regionalism approach
Doğu Asya'da finansal bölgeselciliğin yeni bölgeselcilik yaklaşımı ile bir incelemesi
BURCU ERMEYDAN
Yüksek Lisans
İngilizce
2016
Uluslararası İlişkilerOrta Doğu Teknik ÜniversitesiSiyaset Bilimi ve Uluslararası İlişkiler Ana Bilim Dalı
YRD. DOÇ. DR. YONCA ÖZDEMİR GÜRŞAN
- Semantic video analysis for surveillance systems
Gözetim sistemleri için anlamsal video analizi
KARANİ KARDAŞ
Doktora
Türkçe
2018
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve KontrolOrta Doğu Teknik ÜniversitesiBilgisayar Mühendisliği Ana Bilim Dalı
PROF. DR. AHMET COŞAR
PROF. DR. FEHİME NİHAN ÇİÇEKLİ
- Kentsel kullanımda kamusal mekan pratikleri: Karşıyaka'da (İzmir) toplum merkezleri
Public space practices on urban usage: Community centers in Karsiyaka (Izmir)
NİLAY ÖZCAN USLU
- Uzman sistemler ve ulaştırma alanında kullanımları
Expert systems and using them in transportation
A.BURAK GÖKTEPE
- DÖRT ROTORLU İNSANSIZ HAVA ARAÇLARI İÇİN VERİYE DAYALI KONTROL SİSTEM TASARIMI
DATA DRIVEN CONTROL SYSTEM DESIGN FOR QUADROTOR UNMANNED AERIAL VEHICLES
ATAKAN YILDIZ
Yüksek Lisans
Türkçe
2024
Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrolİstanbul Teknik ÜniversitesiKontrol ve Otomasyon Mühendisliği Ana Bilim Dalı
PROF. DR. AFİFE LEYLA GÖREN