Predicting the Performance of Homestay Entrepreneurs Based on Digital Competencies: Machine Learning Approach

Abstract

This study aimed to predict the performance of homestay entrepreneurs in digital competencies by developing a model using machine learning algorithms. The research adopted the k-Means clustering algorithm to effectively group the performances based on their competency levels, and three distinct machine learning techniques, namely random forest (RF), logistic regression (LR) and k-nearest neighbour (k-NN) were harnessed to evaluate their efficacy in classifying homestay entrepreneurs’ performance levels, namely high, good and average. The RF model achieved a mean accuracy score of 100% which indicates a high level of precision that can effectively predict the performance level of the homestay entrepreneurs based on digital competencies. This is further supported by the Area Under the Curve (AUC) value of 1.0 obtained by the RF model which suggests that the model has achieved optimal separation of the three classes, and therefore it is highly reliable for performance prediction. The application of these technique is believed to enhance the efficiency and accuracy of performance level assessment that could enable entrepreneurs to optimize their decision-making processes and mitigate potential losses caused by the poor performances. Thus, this study demonstrates the effectiveness of machine learning techniques in predicting the business performance levels of homestay entrepreneurs in Malaysia.