This thesis is focused on extracting meaningful statistics for the characterization and classification of biological, medical, and financial data and contains four chapters. The first chapter contains theoretical background on scaling and wavelets, which supports the work in chapters two and three. In the second chapter, we outline a methodology for representing sequences of DNA nucleotides as numeric matrices in order to analytically investigate important structural characteristics of DNA. This methodology involves assigning unit vectors to nucleotides, placing the vectors into columns of a matrix, and accumulating across the rows of this matrix. Transcribing the DNA in this way allows us to compute the 2-D wavelet transformation and assess regularity characteristics of the sequence via the slope of the wavelet spectra. In addition to computing a global slope measure for a sequence, we can apply our methodology for overlapping sections of nucleotides to obtain an evolutionary slope. In the third chapter, we describe various ways wavelet-based scaling may be used for cancer diagnostics. There were nearly half of a million new cases of ovarian, breast, and lung cancer in the United States last year. Breast and lung cancer have highest prevalence, while ovarian cancer has the lowest survival rate of the three. Early detection is critical for all of these diseases, but substantial obstacles to early detection exist in each case. In this work, we use wavelet-based scaling on metabolic data and radiography images in order to produce meaningful features to be used in classifying cases and controls. Computer-aided detection (CAD) algorithms for detecting lung and breast cancer often focus on select features in an image and make a priori assumptions about the nature of a nodule or a mass. In contrast, our approach to analyzing breast and lung images captures information contained in the background tissue of images as well as information about specific features and makes no such a priori assumptions. In the fourth chapter, we investigate the value of social media data in building commercial default and activity credit models. We use random forest modeling, which has been shown in many instances to achieve better predictive accuracy than logistic regression in modeling credit data. This result is of interest, as some entities are beginning to build credit scores based on this type of publicly available online data alone. Our work has shown that the addition of social media data does not provide any improvement in model accuracy over the bureau only models. However, the social media data on its own does have some limited predictive power.

Dans les génomes bactériens, les fréquents transferts horizontaux de gènes (HGT) introduisent des innovations génomiques qui peuvent entraîner la diversification des populations bactériennes. À l'inverse, la recombinaison homologue (RH) au sein des populations homogénéise leurs génotypes, et ainsi renforce leur cohésion. Ces processus d'échange génétique, et la fréquence à laquelle ils interviennent au sein et entre les populations, doivent avoir un grand impact sur la cladogénèse bactérienne. Au-delà de la configuration des échanges qui se sont réellement produits entre les bactéries, les traces de RH et de HGT que nous observons dans leurs génomes reflètent les événements qui ont été fixés tout au long de leur histoire. Ce processus de fixation peut être biaisé en ce qui concerne la nature des gènes ou allèles qui ont été introduits. La sélection naturelle peut notamment conduire à la fixation des gènes transférés qui apportent de nouvelles adaptations écologiques. En outre, des biais mécaniques dans le processus de recombinaison lui-même peuvent conduire à la fixation d'allèles non-adaptatifs. Nous avons cherché à caractériser certains de ces processus adaptatifs et non-adaptatifs qui façonnent les génomes bactériens. À cette fin, plusieurs aspects de l'évolution des génomes, comme les variations de leurs répertoires de gènes, de leur architecture et de leur composition en nucléotides ont été examinés à la lumière de leur histoire de transfert et de recombinaison / In bacterial genomes, the frequent horizontal gene transfers (HGT) introduce genomic novelties that can promote the diversification of bacterial populations. In opposition, homologous recombination (HR) within populations homogenizes their genotypes, enforcing their cohesion. These processes of genetic exchange, and their patterns of occurrence among and within lineages, must have a great impact on bacterial cladogenesis. Beyond the pattern of exchanges actually occurring between bacteria, the traces of HR and HGT we observe in their genomes reflect what events were fixed throughout their history. This fixation process can be biased regarding the nature of genes or alleles that were introduced. Notably, natural selection can drive the fixation of transferred genes that bring new ecological adaptations. In addition, some mechanical biases in the recombination process itself may lead to the fixation of non-adaptive alleles. We aimed to characterize such adaptive and non-adaptive processes that are shaping bacterial genomes. To this end, several aspects of genome evolution, such as variations of their gene repertoires, of their architecture and of their nucleotide composition were examined in the light of their history of transfer and recombination