| Abstract: | The traditional approach of sales and marketing goals no longer help the companies to manage
up with the pace of the competitive market, as they are carried out with no insights to customers’
purchasing patterns. Major transformations can be seen in the domain of sales and marketing as
a result of Machine Learning advancements. Due to such advancements, various critical aspects
such as consumers’ purchase patterns, target audience, and predicting sales for the recent years
to come can be easily determined, thus helping the sales team in formulating plans for a boost in
their business. The aim of this study is to utilize machine learning algorithms to develop a sales
prediction model for Transsion Manufacturing PLC. In this study an attempt is made to apply
machine learning algorithms for mobile phone sales prediction. After performing business and
data understanding the data preparation task is done to clean and make the data ready for
experimentation. For the experiment and construct predictive model, machine learning
algorithms such as Random Forest, KNN, Naïve Bayes and SVM are selected based on their
advantages and past performance seen in different literatures, it has been reported that they
were widely used classifier algorithms for prediction and classification. The Jupyter Notebook with
python programming is employed to simulate all the experiments. Confusion matrix is used to
calculate the accuracy, precision and evaluate the performance of the models.
The results of the experiment show high accuracy, so that the models can be used to predict
mobile phone sales either ITEL or TECNO Brand and either FEATURE phone or SMART phone
accurately. Experimental results show that the Random Forest classifier outperforms other
algorithms with an accuracy of 99.6%, 96.8% in experiment one and two respectively. Therefore,
the Random Forest classifier is proposed for constructing mobile phone sales prediction models
for Transsion Manufacturing. Based on the proposed optimal models in this study, we recommend
future research to integrate mobile phone sales predictive models with mobile phone production
systems. |
