In this paper, following Lu’s (2017) estimator, a difference cum exponential estimator has been proposed using two auxiliary variables to estimate the unknown population mean. The expressions for bias and mean squared error (MSE) of the proposed estimator have been derived up to the first order of approximation. To verify the theoretical results, three real data sets are utilised: one biomedical data set, another from electrical power engineering, and the third is the apple production amount in the Black Sea Region of Turkey. A simulation study is conducted to cross-check empirical results.