Publicação
Enhanced web analytics for health insurance
| Resumo: | Nowadays companies need invest and improve on data solution implementation within most of the business workflows and processes, in order to differentiate the offer and stay ahead of their competitors. It’s becoming more and more important to take data driven decisions to boost profitability and improve the overall customer experience. In this way, strategies are defined not anymore on common beliefs and assumptions, but on contextualized and trustful insights. This reports describes the work that has been made during a 9-month internship, in order to provide the business with a new and improved solution for enhancing the web analytics tasks and supporting the improve of the online user digital experience. User-level data related to the website activity has been extracted at the highest granularity level. Afterwards, raw data have been cleaned and stored in an Analytical Base Table with which an initial data exploration has been made. After giving initial insights to the digital team, a predictive model has been developed in order to predict the probability of the users to buy the insurance product online. Finally, based on the initial data exploration and the model’s results, a set of recommendations has been built and provided to the digital department for their implementation in order to make the website more engaging and dynamic. |
|---|---|
| Autores principais: | Maggi, Piero |
| Assunto: | Web Analytics Google Analytics Supervised Learning Decision Tree Logistic regression Random Forest User Behavior |
| Ano: | 2020 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | Nowadays companies need invest and improve on data solution implementation within most of the business workflows and processes, in order to differentiate the offer and stay ahead of their competitors. It’s becoming more and more important to take data driven decisions to boost profitability and improve the overall customer experience. In this way, strategies are defined not anymore on common beliefs and assumptions, but on contextualized and trustful insights. This reports describes the work that has been made during a 9-month internship, in order to provide the business with a new and improved solution for enhancing the web analytics tasks and supporting the improve of the online user digital experience. User-level data related to the website activity has been extracted at the highest granularity level. Afterwards, raw data have been cleaned and stored in an Analytical Base Table with which an initial data exploration has been made. After giving initial insights to the digital team, a predictive model has been developed in order to predict the probability of the users to buy the insurance product online. Finally, based on the initial data exploration and the model’s results, a set of recommendations has been built and provided to the digital department for their implementation in order to make the website more engaging and dynamic. |
|---|