Predictive analysis for sales: A B2B case

• Main Author: Calixto, Nelito Cravid
• Publication Date: 2019
• Format: Master thesis
• Language: eng
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: http://hdl.handle.net/10071/22203
• topic: Data mining -- Data mining; Predictive analytics; Sales; Performance measurement; Human resources; Extracção de conhecimento em dados; Análise preditiva; Venda; Avaliação do desempenho -- Performance evaluation; Recursos humanos

Measuring salespeople’s performance is a process that occurs multiple times per year on a company. During this process, the manager and the salesperson evaluate how the salesperson performed on numerous Key Performance Indicators (KPIs). To prepare the evaluation meeting, managers have to gather data from Customer Relationship Management, Financial Systems, Excel files, among others, leading to a very time-consuming process. The result of the performance evaluation is a classification followed by actions to improve the performance where it is needed. Nowadays, through predictive analytics technologies, it is possible to make classifications based on data. In this work, the author applied a Naive Bayes model to classify salespeople into pre-defined categories provided by the business, through the use of data mining techniques over a dataset of about three years of sales made by 566 salespeople of a global freight forwarder. The classification is done in 3 classes, being: Not Performing, Good and Outstanding, the classification was achieved based on KPI’s like growth volume and percentage, sales variability along the year, opportunities created, customer baseline, target achievement among others. The author also identified the most critical factors for salesperson’s success based on the dataset as Growth amount, Target achievement, Growth percentage, and the number of months with growth above 0. The author assessed the performance of the model with a confusion matrix and other techniques like True Positives, True Negatives, and F1 score. The results showed an accuracy of 92,10% for the whole model.