Differential evolution based classification with pool of distances and aggregation operators

The objective of this thesis is to develop and generalize further the differential evolution based data classification method. For many years, evolutionary algorithms have been successfully applied to many classification tasks. Evolution algorithms are population based, stochastic search algorithms that mimic natural selection and genetics. Differential evolution is an evolutionary algorithm that has gained popularity because of its simplicity and good observed performance. In this thesis a differential evolution classifier with pool of distances is proposed, demonstrated and initially evaluated. The differential evolution classifier is a nearest prototype vector based classifier that applies a global optimization algorithm, differential evolution, to determine the optimal values for all free parameters of the classifier model during the training phase of the classifier. The differential evolution classifier applies the individually optimized distance measure for each new data set to be classified is generalized to cover a pool of distances. Instead of optimizing a single distance measure for the given data set, the selection of the optimal distance measure from a predefined pool of alternative measures is attempted systematically and automatically. Furthermore, instead of only selecting the optimal distance measure from a set of alternatives, an attempt is made to optimize the values of the possible control parameters related with the selected distance measure. Specifically, a pool of alternative distance measures is first created and then the differential evolution algorithm is applied to select the optimal distance measure that yields the highest classification accuracy with the current data. After determining the optimal distance measures for the given data set together with their optimal parameters, all determined distance measures are aggregated to form a single total distance measure. The total distance measure is applied to the final classification decisions. The actual classification process is still based on the nearest prototype vector principle; a sample belongs to the class represented by the nearest prototype vector when measured with the optimized total distance measure. During the training process the differential evolution algorithm determines the optimal class vectors, selects optimal distance metrics, and determines the optimal values for the free parameters of each selected distance measure. The results obtained with the above method confirm that the choice of distance measure is one of the most crucial factors for obtaining higher classification accuracy. The results also demonstrate that it is possible to build a classifier that is able to select the optimal distance measure for the given data set automatically and systematically. After finding optimal distance measures together with optimal parameters from the particular distance measure results are then aggregated to form a total distance, which will be used to form the deviation between the class vectors and samples and thus classify the samples. This thesis also discusses two types of aggregation operators, namely, ordered weighted averaging (OWA) based multi-distances and generalized ordered weighted averaging (GOWA). These aggregation operators were applied in this work to the aggregation of the normalized distance values. The results demonstrate that a proper combination of aggregation operator and weight generation scheme play an important role in obtaining good classification accuracy. The main outcomes of the work are the six new generalized versions of previous method called differential evolution classifier. All these DE classifier demonstrated good results in the classification tasks.

Omnibus accounts to Finnish investors? – An analysis of the costs and benefits that omnibus account structure brings to Finnish account operators and investors

The Finnish Securities Markets are being harmonized to enable better, more reliable and timely settlement of securities. Omnibus accounts are a common practice in the European securities markets. Finland forbids the use of omnibus accounts from its domestic investors. There is a possibility that the omnibus account usage is allowed for Finnish investors in the future. This study aims to build a comprehensive image to Finnish investors and account operators in determining the costs and benefits that the omnibus account structure would have for them. This study uses qualitative research methods. A literature review provides the framework for this study. Different kinds of research articles, regulatory documents, studies performed by European organisations, and Finnish news reportages are used to analyse the costs and benefits of omnibus accounts. The viewpoint is strictly of account operators and investors, and different effects on them are contemplated. The results of the analysis show that there are a number of costs and benefits that investors and account operators must take into consideration regarding omnibus accounts. The costs are related to development of IT-systems so that participants are able to adapt to the new structure and operate according to its needs. Decrease in the holdings’ transparency is a disadvantage of the structure and needs to be assessed precisely to avoid some problems it might bring. Benefits are mostly related to the increased competition in the securities markets as well as to the possible cost reductions of securities settlement. The costs and benefits were analysed according to the study plan of this thesis and as a result, the significance and impact of omnibus accounts to Finnish investors and account operators depends on the competition level and the decisions that all market participants make when determining if the account structure is beneficial for their operations.