| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 2.37 MB | Adobe PDF |
Authors
Abstract(s)
Recentemente, a empresa ABC, que atua no segmento de mercado B2B e oferece serviços de transformação digital, tem verificado um aumento no volume de Deals e Leads. Este aumento de Deals e Leads tem resultado num aumento da receita da empresa ABC. De modo a prever a receita da empresa ABC, foi utilizada uma abordagem quantitativa, onde se comparou a eficiência dos algoritmos de machine learning Multiple Linear Regression (MLR), Support Vector Regression (SVR) e Multilayer Perceptron (MLP) na previsão da receita mensal, utilizando dados da empresa entre 2017 e o início de 2023. A comparação da eficiência dos algoritmos teve por base duas técnicas: (i) a divisão arbitrária da base de dados em base de treino e base de teste e (ii) a técnica K-Fold cross validation. Usando a primeira técnica, o modelo MLP foi considerado o mais adequado para prever a receita mensal da empresa ABC, tendo em conta as medidas de performance R 2 e Mean Square Error (MSE). No entanto, usando a técnica K-Fold cross validation conclui-se que o modelo SVR tem melhor desempenho na previsão da receita mensal da empresa ABC. Tendo em conta que a técnica K-Fold cross validation utiliza toda a base de dados para treinar e testar os algoritmos, e de certa forma, mitiga a ocorrência de overfitting, pode ser mais justo comparar os modelos com base nesta técnica. Deste modo, o modelo SVR parece ser o algoritmo mais adequado para prever a receita mensal da empresa ABC.
Recently, company ABC, which operates in the B2B market segment and offers digital transformation services, has seen an increase in the volume of Deals and Leads. This increase in Deals and Leads has resulted in an increase in the revenue of company ABC. In order to predict the revenue of company ABC, a quantitative approach was used, where the efficiency of the machine learning algorithms Multiple Linear Regression (MLR), Support Vector Regression (SVR) and Multilayer Perceptron (MLP) in predicting the monthly revenue was compared, using data from the company between 2017 and the beginning of 2023. The comparison of the algorithms efficiency was based on two techniques: (i) the arbitrary division of the database into training base and test base and (ii) the K-Fold cross validation technique. Using the first technique, the MLP model was found to be the most suitable to predict the monthly revenue of company ABC, considering the performance measures R 2 and Mean Square Error (MSE). However, using the K-Fold cross validation technique it is concluded that the SVR model performs better in predicting the monthly revenue of company ABC. Considering that the K-Fold cross validation technique uses the entire database to train and test the algorithms, and in a way, mitigates the occurrence of overfitting, it may be fairer to compare the models based on this technique. Therefore, the SVR model seems to be the most suitable algorithm to predict the monthly revenue of the company ABC.
Recently, company ABC, which operates in the B2B market segment and offers digital transformation services, has seen an increase in the volume of Deals and Leads. This increase in Deals and Leads has resulted in an increase in the revenue of company ABC. In order to predict the revenue of company ABC, a quantitative approach was used, where the efficiency of the machine learning algorithms Multiple Linear Regression (MLR), Support Vector Regression (SVR) and Multilayer Perceptron (MLP) in predicting the monthly revenue was compared, using data from the company between 2017 and the beginning of 2023. The comparison of the algorithms efficiency was based on two techniques: (i) the arbitrary division of the database into training base and test base and (ii) the K-Fold cross validation technique. Using the first technique, the MLP model was found to be the most suitable to predict the monthly revenue of company ABC, considering the performance measures R 2 and Mean Square Error (MSE). However, using the K-Fold cross validation technique it is concluded that the SVR model performs better in predicting the monthly revenue of company ABC. Considering that the K-Fold cross validation technique uses the entire database to train and test the algorithms, and in a way, mitigates the occurrence of overfitting, it may be fairer to compare the models based on this technique. Therefore, the SVR model seems to be the most suitable algorithm to predict the monthly revenue of the company ABC.
Description
Keywords
Multiple linear regression Support vector regression Multilayer perceptron Previsão de vendas Machine learning CRM Sales forecasting