The objective of present study is to empirically examine the socio-economic determinants of crime in Pakistan. The analysis is carried out by using the annual time series data for the period 1973-2014. The dependent variable is total crime rate (per one million population), While the explanatory variables are unemployment, education, income inequality, per capita income, and deterrence variable. The study estimates, the long-run and short-run elasticities of supply of offense function by using ARDL (Autoregressive Distributed Lag model) approach.