Background: A resolve engaged by energy regulators worldwide to curtail the liability of Non-Technical Losses (NTLs) in power is the installation of Smart Meters to measure consumed power. However, power regulators in developing countries are confronted with huge metering gap in an era of momentous energy theft which has resulted in deficits in revenue, debts and ultimately power cuts. Objective: The objective of this research is to predict whether the customers’ who are unmetered are eligible to be metered by identifying worthy and unworthy customers for metering given their bill payment history. Methods: The approach analyses the performance accuracy of some machine learning algorithms on small datasets by exploring the classification abilities of Deep learning, Naïve Bayes, Support Vector Machine and Extreme Learning Machine using data obtained from an electricity distribution company in Nigeria. Results: The performance analysis shows that Naïve Bayes classifier outperformed the Deep Learning, Support Vector Machine and Extreme Learning Machine algorithms. Experiments in deep learning have shown that the alteration of batch sizes has an effect on the outputs. Conclusion: This paper presents a data-driven methodology for the prediction of consumers’ eligibility to be metered. The research has shown the performance of deep learning, Naive Bayes, SVM and ELM on small dataset. The research will help utility companies in developing countries with large populations and huge metering gaps to prioritise the installation of smart meters based on consumer’s payment history.