Felipe Dias Paiva

Decision-making for financial trading: A fusion approach of machine learning and portfolio selection

Abstract Forecasting stock returns is an exacting prospect in the context of financial time series. This study proposes a unique decision-making model for day trading investments on the stock market. In this regard, the model was developed using a fusion approach of a classifier based on machine learning, with the support vector machine (SVM) method, and the mean-variance (MV) method for portfolio selection. The models experimental evaluation was based on assets from the Sao Paulo Stock Exchange Index (Ibovespa). Monthly rolling windows were used to choose the best-performing parameter sets (the in-sample phase) and testing (the out-of-sample phase). The monthly windows were composed of daily rolling windows, with new training of the classifying algorithm and portfolio optimization. A total of 81 parameter arrangements were formulated. To compare the proposed models performance, two other models were suggested: (i) SVM + 1/N, which maintained the process of classifying the trends of the assets that reached a certain target of gain and which invested equally in all assets that had positive signals in their classifications, and (ii) Random + MV, which also maintained the selection of those assets with a tendency to reach a certain target of gain, but where the selection was randomly defined. Then, the portfolios composition was determined using the MV method. Together, the alternative models registered 36 parameter variations. In addition to these two models, the results were also compared with the Ibovespas performance. The experiments were formulated using historical data for 3716 trading days for the out-of-sample analysis. Simulations were conducted without including transaction costs and also with the inclusion of a proportion of such costs. We specifically analyzed the effect of brokerage costs on buying and selling stocks on the Brazilian market. This study also evaluated the classifiers performance, portfolios’ cardinality, and models’ returns and risks. The proposed main model showed significant results, although demand for trading value can be a limiting factor for its implementation. Nonetheless, this study extends the theoretical application of machine learning and offers a potentially practical approach to anticipating stock prices.

Composition of investment portfolios through a combinatorial multiobjective optimization model using CVaR

This paper presents a combinatorial multiobjective optimization methodology to address diversification of investment in portfolios consistent with the market practices, using a “downside risk” measure. To cope with this feature, parallel versions of two evolutionary algorithms are proposed, based on NSGA-II and DEMO. Simulations consider portfolios comprised of shares that participated in the theoretical portfolio of Ibovespa in 2015. In-sample analysis considers graphical analysis, performance measures for diversity solutions and objective space coverage. Out-of-sample analysis is performed comparing the behavior of lower risk and higher return portfolios in relation to measures of risk and return, for several cardinalities.