Improving solutions for analytics services in a mid-sized insurance company
Viljanen, Isabel (2020)
Viljanen, Isabel
2020
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2020052814971
https://urn.fi/URN:NBN:fi:amk-2020052814971
Tiivistelmä
The purpose of this research-oriented thesis is to provide an understanding of the process of improving solutions for analytics services in a mid-sized insurance company. As there is not one solution that would fit for all, Finnish P&C Insurance Ltd will be used as a case company to demonstrate the process and to find a possible solution that could respond to their current situation better. Finding a suitable analysis tool is important in order to improve the quality of data analysis, to respond to the increasing amount of data and case specific problems in data analysis.
In the study, the focus is on reporting and visualization software due to the limited timeframe. Other data analysis solutions such as ETL tools, OLAP processing or database engines are excluded from the possible solutions. The business needs, type of data, user groups and infrastructural requirements and preferences were considered when choosing a suitable solution for the company. The purpose is to compare the current software in use to the alternative software.
The theoretical background will be based on literature review to understand analytics as a phenomenon and to understand the type of data, analytics use cases, end user groups and infrastructural requirements that are specific to the insurance industry. The empirical part uses both qualitative and quantitative analysis.
The empirical part has been divided into two iterations. On the first one, the alternative software will be evaluated based on the requirement list of desired features and capabilities. On the second iteration, the software fulfilling most of the criteria will be tested. A data analysis scenario will be designed and built using the alternative and current software in order to measure query times of the software, and to evaluate restrictively the user interface.
Results and conclusions of the study are presented in the final chapter. According to the analysis made, three different solutions with software were suggested that might benefit the case company. Also, a suggestion of an improvement of the study is presented considering the things that did not fit for the timeframe of this study. These additional points would be to test the suggested software with larger datasets and more complex analysis use cases. In addition, end user group analysis could be carried out and the usability and adaptability for the software usage considered to be done.
In the study, the focus is on reporting and visualization software due to the limited timeframe. Other data analysis solutions such as ETL tools, OLAP processing or database engines are excluded from the possible solutions. The business needs, type of data, user groups and infrastructural requirements and preferences were considered when choosing a suitable solution for the company. The purpose is to compare the current software in use to the alternative software.
The theoretical background will be based on literature review to understand analytics as a phenomenon and to understand the type of data, analytics use cases, end user groups and infrastructural requirements that are specific to the insurance industry. The empirical part uses both qualitative and quantitative analysis.
The empirical part has been divided into two iterations. On the first one, the alternative software will be evaluated based on the requirement list of desired features and capabilities. On the second iteration, the software fulfilling most of the criteria will be tested. A data analysis scenario will be designed and built using the alternative and current software in order to measure query times of the software, and to evaluate restrictively the user interface.
Results and conclusions of the study are presented in the final chapter. According to the analysis made, three different solutions with software were suggested that might benefit the case company. Also, a suggestion of an improvement of the study is presented considering the things that did not fit for the timeframe of this study. These additional points would be to test the suggested software with larger datasets and more complex analysis use cases. In addition, end user group analysis could be carried out and the usability and adaptability for the software usage considered to be done.