<p>The increasing complexity and diversity of count data have motivated the development of flexible discrete probability models using various methodologies. In this article, a new discrete distribution, called the discrete logarithmic-transformed exponential distribution, is proposed using the survival discretization approach. Several important statistical properties of this distribution are derived, including explicit expressions for the probability mass function, cumulative distribution function, and quantile function. Parameter estimation is examined using maximum likelihood estimation, maximum product spacings, and the proportion of zeros method. The finite-sample performance of these estimators is evaluated through Monte Carlo simulation studies, which indicate that maximum likelihood estimation is generally the most efficient estimator, whereas the maximum product spacings method provides more stable and reliable estimates when the parameter values are small or the sample size is limited. The fitting capability of the proposed distribution is assessed using a real data application, demonstrating its effectiveness for modeling over-dispersed count data.</p>