Predicting market movement with Artificial Neural Networks

This paper presents an application of an Artificial Neural Network (ANN) to the prediction of stock market direction in the US. Using a multilayer perceptron neural network and a backpropagation algorithm for the training process, the model aims at learning the hidden patterns in the daily movement of the S&P500 to correctly identify if the market will be in a Trend Following or Mean Reversion behavior. The ANN is able to produce a successful investment strategy which outperforms the buy and hold strategy, but presents instability in its overall results which compromises its practical application in real life investment decisions.

Using artificial neural networks to generate trading signals for crude oil, copper and gold futures

In this thesis, a feed-forward, back-propagating Artificial Neural Network using the gradient descent algorithm is developed to forecast the directional movement of daily returns for WTI, gold and copper futures. Out-of-sample back-test results vary, with some predictive abilities for copper futures but none for either WTI or gold. The best statistically significant hit rate achieved was 57% for copper with an absolute return Sharpe Ratio of 1.25 and a benchmarked Information Ratio of 2.11.

Cities and emerging networks of learning communities

In the 21st century the majority of people live in urban settings and studies show a trend to the increase of this phenomenon. Globalisation and the concentration of multinational and clusters of firms in certain places are attracting people who seek employment and a better living. Many of those agglomerations are situated in developing countries, representing serious challenges both for public and private sectors. Programmes and initiatives in different countries are taking place and best practices are being exchanged globally. The objective is to transform these urban places into sustainable learning cities/regions where citizens can live with quality. The complexity of urban places, sometimes megacities, opened a new field of research. This paper argues that in order to understand the dynamics of such a complex phenomenon, a multidisciplinary, systemic approach is needed and the creation of learning cities and regions calls for the contribution of a multitude of fields of knowledge, ranging from economy to urbanism, educational science, sociology, environmental psychology and others.

Cognitive assessment of topological movement Patterns and direction turns: An influence of scale

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

TV advertisement and social networks: an empirical study with young adults

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Management from the NOVA – School of Business and Economics

Spatial Patterns and Irregularities of the electoral data: general elections in Canada

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Uncertainty, generalization, and neural representation of relevant variables for decision making

Dissertation presented to obtain the Ph.D degree in Biology, Computational Biology.

Structural transformation in the product space: Patterns and implications

Product fundamentals are essential in explaining heterogeneity in the product space. The scope for adapting and transferring capabilities into the production of different goods determines the speed and intensity of the structural transformation process and entails dissimilar development opportunities for nations. Future specialization patterns become then partly determined by the current network of products’ relatedness. Building on previous literature, this paper explicitly compares methodological concepts of product connectivity to conclude in favor of the density measure we propose combined with the Revealed Relatedness Index (RRI) approach presented by Freitas and Salvado (2011). Overall, RRI specifications displayed more consistent behavior when different time horizons are equated.