In this paper we propose a hybrid metaheuristic based on Particle Swarm Optimization, which we tailor on a portfolio selection problem. To motivate and apply our hybrid metaheuristic, we reformulate the portfolio selection problem as an unconstrained problem, by means of penalty functions in the framework of the exact penalty methods. Our metaheuristic is hybrid as it adaptively updates the penalty parameters of the unconstrained model during the optimization process. In addition, it iteratively refines its solutions to reduce possible infeasibilities. We report also a numerical case study. Our hybrid metaheuristic appears to perform better than the corresponding Particle Swarm Optimization solver with constant penalty parameters. It performs similarly to two corresponding Particle Swarm Optimization solvers with penalty parameters respectively determined by a REVAC-based tuning procedure and an irace-based one, but on average it just needs less than 4% of the computational time requested by the latter procedures.
1 November 2012 in Expert Systems with Applications
The banks' need of quantitative approaches for credit risk assessment is becoming more and more evident, due to the introduction of the Basel agreements. To this extent, we define an Elman network approach to determine the insolvency of a borrower, and compare its performances with classical neural networks approaches for bankruptcy prediction. Then, we devise an adaptive procedure to select the best network topology, by performing a multi-objective analysis to take into account different compromises between conflicting criteria. We apply our procedure to different real and partly-artificial-case scenarios composed of Italian SMEs by using predictors coming from balance-sheet ratios, credit-history ratios and macro-economic indicators; then, we compare our approach to other ones proposed in the literature and to a standard logistic regression tool used by practitioners; last, given the recent research interest towards the use of qualitative predictors in credit risk assessment, we also apply our approaches on qualitative data. The results show that the Elman networks are effective in assessing credit risk and robust with respect to criteria and data, confirming the applicability of neural networks to bankruptcy prediction. Our contribution adds to the discussion of the ongoing debate about comparing neural networks to standard techniques: in particular, we find Elman Networks to lead to lower classification errors than standard feed-forward networks, whilst results from the comparison to logistic regression vary with respect to the error class considered. As for the data, we remark that the use of macro-economics indicators does not lead to particular improvement in classification accuracy, except when used to improve results coming from the use of qualitative variables only.
Cryptocurrencies are nowadays seen as an investment opportunity, since they show some peculiar features, such as high volatility and diversification properties, that are triggering research interest into investigating their differences with traditional assets. In our paper, we address the problem of predictability of cryptocurrency and stock trends by using data from social online communities and platforms to assess their contribution in terms of predictive power. We extend recent developments in the field by exploiting a combination of stochastic neural networks (NNs), an extension of standard NNs, natural language processing (NLP) to extract sentiment from Twitter, and an external evolutionary algorithm for optimal parameter setting to predict the short-term trend direction. Our results point to good and robust accuracy over time and across different market regimes. Furthermore, we propose to exploit recent advances in sentiment analysis to reassess its role in financial forecasting; in this way, we contribute to the empirical literature by showing that predictions based on sentiment analysis are not found to be significantly different from predictions based on historical data. Nonetheless, compared to stock markets, we find that the accuracy of trend predictions with sentiment analysis is on average much higher for cryptocurrencies.
28 August 2015 in Computational Management Science