National Technical University of Athens (NTUA)
A market approach to forecasting: background, theory and practice
Abstract
dc:descriptionMy PhD Thesis focuses on the omnipresent problem of business forecasting. In its very core, theproblem refers to estimating a variable’s future price, potentially being correlated to a set of variables,or ideally following a specific pattern. There exists a variety of statistical approaches, ranging fromclassical econometric techniques to recent data mining algorithms, attempting to extract suchunderlying relationships from past data and reproduce them to predict future values. However, inpractice, these correlations are highly dynamic and patterns, if any, usually evolve in chaotic ways.Therefore even highly adjustable machine learning techniques tend to perform poorly, suffering frominherent systemic impotencies.Human experts, on the other hand, seem to be better suited to address this request. A single expertcan process a big number of variables and quickly adjust predictions into varying circumstances.However, bias and shortcomings reduce the value of such estimates. Consequently, there lies a needand opportunity to develop mechanisms that can demonstrate a capacity to aggregate information fromexperts, in a dynamic, cost and time-effective manner that negates their inherent shortcomings.Financial markets arise as an emerging paradigm to handle such a request. Well- established marketinstitutions typically focus on serving either investment, hedging or speculation purposes, while theirfundamental function of information aggregation remains latent in all but newly, and yet of limitedexposure, prediction markets institutions. I provide a market topology scheme and locate existingmarket institutions in terms of usage of these ubiquitous functions. And I am studying predictionmarkets in this Thesis.I start with a survey. I provide an extensive literature review of the field and a detailed classificationscheme of the existing literature, both appearing for the first time in the bibliography. I then move on toidentify inappropriate attributes ensued from market mechanisms typically used to serve a predictionmarket institution. I build on the latest advances of market scoring rules and dynamic pari-mutuelmarkets to propose an analytical framework for a coherent price function of a dynamic pari-mutuelmarket. I construct and validate a function satisfying this framework, finally contributing what may beperceived as a coherent hybrid between dynamic pari-mutuel market and market scoring rules.I also provide an attempt to evaluate the hybrid’s performance by shaping a dynamic market model and simulating various agent behaviors and strategies to study the properties of convergence, acquisition ofrecently arrived information and equilibrium, among others.I then proceed from models and simulations to practice. To examine the behavior of the proposedmarket mechanism and its forecasting capacity, I build and present a fully-scaled web platform,AskMarkets. Taking advantage of it, I run and analyze a number of experiments in a variety ofacademic, professional and social contexts to empirically validate the applicability of theoreticalfindings. I also provide a practical deployment framework for prediction markets implementation,leveraging on the experience accumulated due to the extent of this study.I also address some advanced concepts and the open question of prediction markets efficiency. Iapproach it by studying the convolution of market prices and relevant news streams. I empiricallyvalidate the approach using the most varied data set of real-money prediction markets contracts everexamined. I finally propose a sophisticated analytical technique for prediction markets to serve forevent detection and eliciting market inefficiencies.Overall, I believe that this Thesis provides a unique contribution to the field of prediction markets,forecasting, decision sciences and operations research at large, studying the mechanism at full scale,ranging from an extensive literature review to a coherent market mechanism and from market modelingto simulations and extended case studies.The Thesis was completed in 2008, yet its defense took place in June 2013.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2014
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Tziralis, Georgios
- Τζιραλής, Γεώργιος
Subjects
dc:subject × 14- Αγορές προβλέψεων
- Προγνωστική
- Επιχειρησιακή έρευνα
- Prediction markets
- Forecasting
- Operations research
- Επιστήμες Μηχανικού και Τεχνολογία
- Επιστήμη Μηχανολόγου Μηχανικού
- Κοινωνικές Επιστήμες
- Οικονομικά και Επιχειρήσεις
- Engineering and Technology
- Mechanical Engineering
- Social Sciences
- Economics and Business
Rights
dc:rights- Statement dc:rights
-
- BY_SA
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/35505