The use of analytical techniques for fraud detection and the design of fraud detection systems have been topics of several research projects in the past and have seen varying degrees of success in their practical implementation. In particular, several authors regard the use of credit risk scorecards for fraud detection as a useful analytical detection tool. However, research on analytical fraud detection for the South African insurance industry is limited. Furthermore, real world restrictions like the availability and quality of data elements, highly unbalanced datasets, interpretability challenges with complex analytical techniques and the evolving nature of insurance fraud contribute to the on-going challenge of detecting fraud successfully. Insurance organisations face financial instability from a global recession, tighter regulatory requirements and consolidation of the industry, which implore the need for a practical and effective fraud strategy. Given the volumes of structured and unstructured data available in data warehouses of insurance organisations, it would be sensible for an effective fraud strategy to take into account data-driven methods and incorporate analytical techniques into an overall fraud risk assessment system. Having said that, the complexity of the analytical techniques, coupled with the effort required to prepare the data to support it, should be carefully considered as some studies found that less complex algorithms produce equal or better results. Furthermore, an over reliance on analytical models can underestimate the underlying risk, as observed with credit risk at financial institutions during the financial crisis. An attractive property of the structure of the probabilistic weights-of-evidence (WOE) formulation for risk scorecard construction is its ability to handle data issues like missing values, outliers and rare cases. It is also transparent and flexible in allowing the re-adjustment of the bins based on expert knowledge or other business considerations. The approach proposed in the study is to construct fraud risk scorecards at entity level that incorporate sets of intrinsic and relational risk factors to support a robust fraud risk assessment. The study investigates the application of an integrated Suspicious Activity Assessment System (SAAS) empirically using real-world South African insurance data. The first case study uses a data sample of short-term insurance claims data and the second a data sample of life insurance claims data. Both case studies show promising results. The contributions of the study are summarised as follows: The study identified several challenges with the use of an analytical approach to fraud detection within the context of the South African insurance industry. The study proposes the development of fraud risk scorecards based on WOE measures for diagnostic fraud detection, within the context of the South African insurance industry, and the consideration of alternative algorithms to determine split points. To improve the discriminatory performance of the fraud risk scorecards, the study evaluated the use of analytical techniques, such as text mining, to identify risk factors. In order to identify risk factors from large sets of data, the study suggests the careful consideration of both the types of information as well as the types of statistical techniques in a fraud detection system. The types of information refer to the categories of input data available for analysis, translated into risk factors, and the types of statistical techniques refer to the constraints and assumptions of the underlying statistical techniques. In addition, the study advocates the use of an entity-focused approach to fraud detection, given that fraudulent activity typically occurs at an entity or group of entities level. / PhD, Operational Research, North-West University, Vaal Triangle Campus, 2011

The use of analytical techniques for fraud detection and the design of fraud detection systems have been topics of several research projects in the past and have seen varying degrees of success in their practical implementation. In particular, several authors regard the use of credit risk scorecards for fraud detection as a useful analytical detection tool. However, research on analytical fraud detection for the South African insurance industry is limited. Furthermore, real world restrictions like the availability and quality of data elements, highly unbalanced datasets, interpretability challenges with complex analytical techniques and the evolving nature of insurance fraud contribute to the on-going challenge of detecting fraud successfully. Insurance organisations face financial instability from a global recession, tighter regulatory requirements and consolidation of the industry, which implore the need for a practical and effective fraud strategy. Given the volumes of structured and unstructured data available in data warehouses of insurance organisations, it would be sensible for an effective fraud strategy to take into account data-driven methods and incorporate analytical techniques into an overall fraud risk assessment system. Having said that, the complexity of the analytical techniques, coupled with the effort required to prepare the data to support it, should be carefully considered as some studies found that less complex algorithms produce equal or better results. Furthermore, an over reliance on analytical models can underestimate the underlying risk, as observed with credit risk at financial institutions during the financial crisis. An attractive property of the structure of the probabilistic weights-of-evidence (WOE) formulation for risk scorecard construction is its ability to handle data issues like missing values, outliers and rare cases. It is also transparent and flexible in allowing the re-adjustment of the bins based on expert knowledge or other business considerations. The approach proposed in the study is to construct fraud risk scorecards at entity level that incorporate sets of intrinsic and relational risk factors to support a robust fraud risk assessment. The study investigates the application of an integrated Suspicious Activity Assessment System (SAAS) empirically using real-world South African insurance data. The first case study uses a data sample of short-term insurance claims data and the second a data sample of life insurance claims data. Both case studies show promising results. The contributions of the study are summarised as follows: The study identified several challenges with the use of an analytical approach to fraud detection within the context of the South African insurance industry. The study proposes the development of fraud risk scorecards based on WOE measures for diagnostic fraud detection, within the context of the South African insurance industry, and the consideration of alternative algorithms to determine split points. To improve the discriminatory performance of the fraud risk scorecards, the study evaluated the use of analytical techniques, such as text mining, to identify risk factors. In order to identify risk factors from large sets of data, the study suggests the careful consideration of both the types of information as well as the types of statistical techniques in a fraud detection system. The types of information refer to the categories of input data available for analysis, translated into risk factors, and the types of statistical techniques refer to the constraints and assumptions of the underlying statistical techniques. In addition, the study advocates the use of an entity-focused approach to fraud detection, given that fraudulent activity typically occurs at an entity or group of entities level. / PhD, Operational Research, North-West University, Vaal Triangle Campus, 2011

This thesis aims to predict the probable undiscovered geothermal systems through investigation of spatial relation between geothermal occurrences and its surrounding geological phenomenon in Western Anatolia. In this context, four different public data, which are epicenter map, lineament map, Bouger gravity anomaly and magnetic anomaly maps, are utilized. In order to extract the necessary information for each map layer the raw public data is converted to a synthetic data which are directly used in the analysis. Synthetic data employed during the investigation process include Gutenberg-Richter b-value map, distance to lineaments map and distance to major grabens present in the area. Thus, these three layers including directly used magnetic anomaly maps are combined by means of Boolean logic model and Weights of Evidence method (WofE), which are multicriteria decision methods, in a Geographical Information System (GIS) environment. Boolean logic model is based on the simple logic of Boolean operators, while the WofE model depends on the Bayesian probability. Both of the methods use binary maps for their analysis. Thus, the binary map classification is the key point of the analysis. In this study three different binary map classification techniques are applied and thus three output maps were obtained for each of the method. The all resultant maps are evaluated within and among the methods by means of success indices. The findings reveal that the WofE method is better predictor than the Boolean logic model and that the third binarization approach, which is named as optimization procedure in this study, is the best estimator of binary classes due to obtained success indices. Finally, three output maps of each method are combined and the favorable areas in terms of geothermal potential are produced. According to the final maps the potential sites appear to be Aydin, Denizli and Manisa, of which first two have been greatly explored and exploited since today and thus not surprisingly found as potential in the output maps, while Manisa when compared to first two is nearly virgin.

The research undertaken in this dissertation was designed to explore how the institutionalized social inequalities in prehistoric Woodland society are reflected in the differences in the procurement, in the life history, and the final discard locations of the flaked chert stone tools from the Crystal River site (8CI1). The Woodland period (1000 BC to AD 1000) was a time of both stability and change in Native American society. Many of the core institutions such as subsistence, hunting and ceramic technology, and residence remained relatively constant while religious and political institutions underwent dramatic changes. This study focuses on how these social inequalities were manifested in the chipped stone tool assemblage from this site. The Crystal River site is an Early to Middle Woodland-period mound complex located in coastal Citrus County, Florida. Dedicated as a National Historic Landmark site in 1991, the Crystal River site is internationally known and respected. Despite extensive work at the site conducted by Bullen and others during the 1940-60s, little was actually published about the material remains excavated from the site. Work resumed on the site in the 1980s and has continued as required by park maintenance and repair issues. Since 2007, remote sensing and other non-invasive technologies have been employed to advance research further at the site. This research returned to the flaked stone materials recovered during the periods 1903-1964 and 1984-2001 to illuminate site activities better without additional ground-disturbing activities. Multiple techniques were employed to develop the data sets that were used to investigate the research questions addressed in this study. The GIS-based weights-of-evidence procedure was used to predict the locations of chert outcrops within a 50 km study area. This model validated the existing quarry cluster method of determining the provenience of Florida cherts. A cost-path analysis was used to identify those chert sources that would have been most accessible to the site's inhabitants. These techniques defined a series of coastal chert outcrops that form the newly-proposed New Coastal quarry cluster. A chaîne opératoire or operational sequence approach was adopted for the analysis of the chipped stone assemblage. A waste flake analysis, a hafted biface classification, and a raw material provenience classification were conducted for all flaked-stone materials. Use-wear determinations were made using both low-power (10-70x) and high-power (50-400x) magnification analysis techniques. A life history approach was taken to the hafted biface assemblage and hafted biface retouch index (HRI) values were determined for all hafted bfaces and biface fragments. The provenience analysis demonstrated that the majority of the chert used by the inhabitants of Crystal River came from outcrops and quarries south of the site along the coastal marshes and the western margins of the Brooksville Ridge. These resources are all within a short canoe trip from the site. Two life history trajectories are suggested for the chipped stone tools from Crystal River. The majority of the chert was obtained from local sources. The second life history was defined for a small subset of the hafted bifaces that were transported from quarries located outside the core subsistence catchment of Crystal River site. Four research hypotheses were developed to test propositions related to the ways in which institutionalized social inequalities are reflected in the patterning of the chipped stone artifact assemblage at the Crystal River site. Although only some of these hypotheses were supported, the results of this investigation do support much of the research that has previously been conducted with the lithic assemblages from Woodland mound complexes in Florida. Chert acquisition is heavily reliant on local lithic sources. Chert procurement appears to be embedded in the collection of other resources. Stone tool use at the site follows the typical expedient flake tool/local raw material pattern that has been documented for other Middle Woodland sites in the region. There was no evidence to suggest that thermal alteration was used to enhance the quality of either the local cherts or those brought to the site from more distant sources. The analysis identified two distinct life histories for at least part of the stone tool assemblage. Many of the hafted bifaces, formed tools and flake tools recovered from the site were made from local cherts. These tool where likely made, used, and discarded at Crystal River. Some of the hafted bifaces and flake cores were made from cherts found on the outer edges of the 50 km study area defined for this investigation. These items were brought to the Crystal River site, used, resharpened, and broken in transit, and finally replaced by new tools at the site. The broken fragments of these tools were discarded in the midden debris to eventually become part of the archaeological record from this now-famous site.

The dynamic modeling process is a useful tool for the knowledge of land use and occupation, creating methodological guidelines associated to ambient, social and economical issues. This work aims to establish a model to simulate the dynamic in the sandfication process and forest cover at South-west of Rio Grande do Sul, named micro regions of Campanha Ocidental and, based on this technics, make a future scenery projection. An image mosaic of LANDSAT 5 satellite was used, which recovers the studied region in the years of 1985, 1996, 2011 and LANDSAT 8 in 2013 year. SPRING was used to data base elaboration and data processing of digital images. After the image classification, the LEGAL program was used to develop the cross thematic maps, which will be used on simulations for the future sceneries by modeling with Dinamica EGO software. The expected results for 2026 indicate that forest cover will increase from 14.22% in 2011 to 15,03% in the year 2026 the total area of the Campanha Ocidental, showing that the expansion of forest cover is in the process of stabilization, focusing the areas in east, high altitudes and around drainage rivers. In the sand, this projection will retracts from 0.37% in 2011 to 0.33% in 2026, its concentration will be in the northeast, high altitudes and around the Ibicuí river drainage. / A modelagem dinâmica é uma ferramenta útil para o conhecimento do uso e ocupação da terra, gerando diretrizes metodológicas associadas às questões ambientais, sociais e econômicas. Este trabalho teve por objetivo aplicar um modelo para simular a dinâmica no processo de arenização e cobertura florestal do Sudoeste do Rio Grande do Sul, denominada microrregião da Campanha Ocidental e, com base nessas técnicas, efetuar a projeção de cenários futuros. Foi utilizado um mosaico de imagens do satélite LANDSAT 5 sensor TM, que recobre a região de estudo nos anos de 1985, 1996 e 2011 e LANDSAT 8 sensor OLI no ano de 2013. Para elaboração da base de dados e processamento digital das imagens, utilizou-se o aplicativo SPRING. Após a classificação das imagens, foi realizado o cruzamento dos mapas temáticos com auxílio da programação LEGAL, e posteriormente, empregado a simulação dos cenários futuros por meio da modelagem com o aplicativo Dinamica EGO. Os resultados previstos para 2026 indicam que a cobertura florestal irá se expandir de 14,22% em 2011 para 15,03% no ano de 2026 da área total da Campanha Ocidental, demonstrando que o aumento da cobertura florestal encontra-se em processo de estabilização, concentrando-se suas áreas na parte leste, altitudes elevadas e nas bordas da rede de drenagem. Nos areais, a projeção demonstrou que sua área sofrerá retração de 0,37% em 2011 para 0,33% da área total da região em 2026, e sua concentração estará presente na parte leste, em altitudes elevadas e em torno da drenagem do rio Ibicui.