Publicação
Pharmaceutical Sales Representatives´ Performance and Impact on Revenue - Using a Data Mining Approach
| Resumo: | With the growing number of health disorders on the global level, the pharmaceutical industry has evolved in developing and producing medicines and drugs that improve the quality of life. It is thus desired to make all pharmaceuticals reach a vast number of people worldwide and to fulfill that purpose more promptly the Pharmaceutical Sales Representatives are the vital reference for selling pharmaceuticals to physicians and all sorts of health companies. They are the main source of information for the latest drugs in the market including the ones from their own company and do not make direct sales as they only aim to build their network and relationships with potential clients by setting one-on-one meetings with physicians. In this context, the present research uses a Data Mining approach following the CRISP-DM methodology and Unsupervised Learning techniques to analyze the performance of a Pharmaceutical Sales Representatives team engaged with a certain pharmaceutical company over the years and the consequent impact that it has had in the company’s sales. This assessment was conducted by using a combination of Hierarchical Clustering with K-Modes to segment the data provided by the company and it presented four initial clusters, each demonstrating the level of acceptance of a meeting by a physician, the meeting’s most valuable Therapeutic areas, the number of products and physicians addressed and finally the meeting’s feedback provided from the Pharmaceutical Sales Representative after the visit. Finally, all clusters were merged using Hierarchical Clustering once more to avoid complexity and new other four segments were obtained describing four groups of interactions within the data. All results found met this research expectations and all types of interactions were explored to corroborate the effectiveness of the Pharmaceutical Sales Representatives team of the present pharmaceutical company. |
|---|---|
| Autores principais: | Candeias, Leonor de Almeida |
| Assunto: | Data Mining Unsupervised Learning Clustering Pharmaceutical Sales Representative Sales SDG 3 - Good health and well-being SDG 8 - Decent work and economic growth SDG 9 - Industry, innovation and infrastructure SDG 10 - Reduced inequalities SDG 12 - Responsible production and consumption SDG 15 - Life on land SDG 16 - Peace, justice and strong institutions |
| Ano: | 2024 |
| 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: | With the growing number of health disorders on the global level, the pharmaceutical industry has evolved in developing and producing medicines and drugs that improve the quality of life. It is thus desired to make all pharmaceuticals reach a vast number of people worldwide and to fulfill that purpose more promptly the Pharmaceutical Sales Representatives are the vital reference for selling pharmaceuticals to physicians and all sorts of health companies. They are the main source of information for the latest drugs in the market including the ones from their own company and do not make direct sales as they only aim to build their network and relationships with potential clients by setting one-on-one meetings with physicians. In this context, the present research uses a Data Mining approach following the CRISP-DM methodology and Unsupervised Learning techniques to analyze the performance of a Pharmaceutical Sales Representatives team engaged with a certain pharmaceutical company over the years and the consequent impact that it has had in the company’s sales. This assessment was conducted by using a combination of Hierarchical Clustering with K-Modes to segment the data provided by the company and it presented four initial clusters, each demonstrating the level of acceptance of a meeting by a physician, the meeting’s most valuable Therapeutic areas, the number of products and physicians addressed and finally the meeting’s feedback provided from the Pharmaceutical Sales Representative after the visit. Finally, all clusters were merged using Hierarchical Clustering once more to avoid complexity and new other four segments were obtained describing four groups of interactions within the data. All results found met this research expectations and all types of interactions were explored to corroborate the effectiveness of the Pharmaceutical Sales Representatives team of the present pharmaceutical company. |
|---|