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.

Carry and trend-following strategies

Recent research has shown that carry and trend strategies when combined lead to significant risk-adjusted returns that can be very attractive to investors, at a low cost with small and positive skewness. This study proposes to combine both carry and trend-following, considering a data set of ten years (09/2005-09/2015), within a portfolio composed by three major asset classes: currencies, commodities and equity indices. Following a futures-based methodology, the obtained results show that, indeed, the strategy results inevitably in higher returns and greater sharpe ratios for every asset class in study. This outcome results from the fact that trend proved to provide a significant hedge to the downside risk that carry is exposed to.

Leverage instability and persistence: Evidence from the United States and Europe

We find that leverage behavior both in level and time-series variation is very similar between the United States and Europe throughout the 1990-2013 period. Leverage regimes are simultaneously unstable and persistent for both regions. We define instability as the extent to which firms largely deviate from their long-term leverage mean, while persistence as the extent to which today’s leverage influences its future levels. We then show that this simultaneous evidence imply a mean-reversion behavior of leverage and discuss some of its implications for future research on this field.

Valuing an offshore exploration project through real options analysis

This thesis applied real options analysis to the valuation of an offshore oil exploration project, taking into consideration the several options typically faced by the management team of these projects. The real options process is developed under technical and price uncertainties, where it is considered that the mean reversion stochastic process is more adequate to describe the movement of oil price throught time. The valuation is realized to two case scenarios, being the first a simplified approach to develop the intuition of the used concepts, and the later a more complete cases that is resolved using both the binomial and trinomial processes to describe oil price movement. Real options methodology demonstrated to be capable of assessing and valuing the projects options, and of overcoming common capital budgeting methodologies flexibility limitation. The added value of the application of real options is evident, but so is the method's increased complexity, which adversely influence its widespread implementation.

An equity wealth preservation strategy: Following the macro trend

Financial crisis have happened in the past and will continue to do so in the future. In the most recent 2008 crisis, global equities (as measured by the MSCI ACWI index) lost a staggering 54.2% in USD, on the year. During those periods wealth preservation becomes at the top of most investor’s concerns. The purpose of this paper is to develop a strategy that protects the investment during bear markets and significant market corrections, generates capital appreciation, and that can support Millennium BCP’s Wealth Management Unit on their asset allocation procedures. This strategy extends the Dual Momentum approach introduced by Gary Antonacci (2014) in two ways. First, the investable set of securities in the equities space increases from two to four. Besides the US it will comprise the Japanese, European (excl. UK) and EM equity indices. Secondly, it adds a volatility filter as well as three indicators related to the business cycle and the state of the economy, which are relevant to decide on the strategy’s exposure to equities. Overall the results attest the resiliency of the strategy before, during and after historical financial crashes, as it drastically reduces the downside exposure and consistently outperforms the benchmark index by providing higher mean returns with lower variance.