Viorel Milea

An Automated Framework for Incorporating News into Stock Trading Strategies

In this paper we present a framework for automatic exploitation of news in stock trading strategies. Events are extracted from news messages presented in free text without annotations. We test the introduced framework by deriving trading strategies based on technical indicators and impacts of the extracted events. The strategies take the form of rules that combine technical trading indicators with a news variable, and are revealed through the use of genetic programming. We find that the news variable is often included in the optimal trading rules, indicating the added value of news for predictive purposes and validating our proposed framework for automatically incorporating news in stock trading strategies.

A multi-covariate semi-parametric conditional volatility model using probabilistic fuzzy systems

Value at Risk (VaR) has been successfully estimated using single covariate probabilistic fuzzy systems (PFS), a method which combines a linguistic description of the system behaviour with statistical properties of data. In this paper, we consider VaR estimation based on a PFS model for density forecast of a continuous response variable conditional on a high-dimensional set of covariates. The PFS model parameters are estimated by a novel two-step process. The performance of the proposed model is compared to the performance of a GARCH model for VaR estimation of the S&P 500 index. Furthermore, the additional information and process understanding provided by the different interpretations of the PFS models are illustrated. Our findings show that the validity of GARCH models are sometimes rejected, while those of PFS models of VaR are never rejected. Additionally, the PFS model captures both instant and periods of high volatility, and leads to less conservative models.

Prediction of the MSCI EURO index based on fuzzy grammar fragments extracted from European Central Bank statements

We focus on predicting the movement of the MSCI EURO index based on European Central Bank (ECB) statements. For this purpose we learn and extract fuzzy grammars from the text of the ECB statements. Based on a set of selected General Inquirer (GI) categories, the extracted fuzzy grammars are grouped around individual content categories. The frequency at which these fuzzy grammars are encountered in the text constitute input to a Fuzzy Inference System (FIS). The FIS maps these frequencies to the levels of the MSCI EURO index. Ultimately, the goal is to predict whether the MSCI EURO index will exhibit upward or downward movement based on the content of ECB statements, as quantified through the use of fuzzy grammars and GI content categories.

A new Airport Collaborative Decision Making algorithm based on Deferred Acceptance in a two-sided market

We present a novel approach for Compression in Collaborative Decision Making.This is the first approach to include the preferences of Airport Management.The optimal allocation is obtained by an application of the Deferred Acceptance algorithm.Our proposed method always provides a stable result.The initial order of any original schedule does not affect the stable allocation. The main objective of Airport Collaborative Decision Making (A-CDM) is to allow the stakeholders working together in more efficiently and transparently way to share data and to enhance Air Traffic Management (ATM) processes. The state-of-the-art approaches for A-CDM, currently implemented in many airports in both Europe as well as the United States, are considered mature and well accepted. In many cases it usually focuses on the information sharing and only takes into account the preferences of Air Traffic Control (ATC) units and those of the airlines. This inherently leads to only satisfying the preferences of a limited number of stakeholders within the airport area. In this paper we extend current state-of-the-art approaches to include the preferences of the Airport Management in the A-CDM. The model that we propose is based on the Deferred Acceptance (DA) allocation mechanism from Game Theory and addresses the problem of slot allocation in the Compression step of the classic CDM algorithm currently used. Dealing with this market by using the DA-CDM model enables assigning flights to slots through a one-to-one relationship that respects the preferences of each allocation and is always guaranteed to provide a stable result.

Collaborative Decision Making in Departure Sequencing With an Adapted Rubinstein Protocol

Collaborative decision making (CDM) is an operational paradigm where the decisions are based on complete, shared, and up-to-date information among all the stakeholders involved in air traffic flow management. Such stakeholders include air traffic controllers and airlines. However, in Brazil, these operations are still coordinated manually by human controllers. We propose a novel, collaborative approach to decide departure sequencing in airports using game theory. Each aircraft is represented as a player in the negotiation process for slot allocation. The collaborative departure management (CoDMAN) system that we propose is designed to provide efficient departure sequencing based on the negotiation among the aircraft in a dynamic scenario modeled under the Rubinstein protocol and CDM principles. A prototype of this system is used to simulate real-world scenarios based on actual flight plans from the Brasília terminal control area (TMA). Using CoDMAN for departure sequencing reduces the observed delays of aircraft.

Metafrastes: A News Ontology-Based Information Querying Using Natural Language Processing

This paper presents Metafrastes, a system that provides users with the ability to retrieve information from Semantic Web knowledge bases through queries that are formulated in natural language. The Web system that we introduce is engineered based on several Semantic Web tools and techniques. Our contribution consists mainly of a Natural Language Processing engine, able to translate queries formulated in natural language to SPARQL queries that can be applied to existing knowledge bases. Additionally, we develop a user interface that captures the user interaction with the system. Last, we evaluate the system based on a number of pre-defined queries formulated in natural language. The proposed approach has been positively evaluated with respect to precision and for queries that are aware of the information structure from the knowledge base.

A framework for Web news items analysis in relation to share prices

We present a general approach for Web news items analysis in relation to stock prices. The framework that we introduce provides the ability to study the impact of events extracted from news on stock prices. The relation between events and price is quantified in terms of the i) paired-samples t-test, ii) McNemars test, and iii) confidence and support. The extraction, representation, and visualization of data are key components of the proposed framework. The validation of the framework is based on three case studies, involving Tesco, Shell, and British Petroleum, and the price reaction(s) to different news events.

Semantic Web-Based Product Search

Product search on the Web has become increasingly popular for consumers to find products of interest. This paper proposes SWEPS, a platform inspired by concepts from the Semantic Web, for the purpose of effective and efficient product search. The proposed platform consists of modules that are responsible for the retrieval, integration, aggregation, and presentation of product information on the Web. The main goal is to reduce the consumer effort when searching and browsing for desired products. In order to test the viability of the proposed approach, we also present an adequate evaluation methodology for the proposed platform.