Ancient DNA provides a unique means to track the neutral and adaptive changes as they emerged in past populations. The time-series nature of aDNA may allow us to identify when and in which population adaptive variation arose, its trajectory to fixation and hypothesize cause of its change in frequency. Recent theoretical works have shown, however, that the interaction between the signal of demographic changes and selection can lead to bias in the inference of population size changes, migration rates, and the spurious identification of adaptive loci in genome scans. In this context, the joint estimation of selection and demography is a necessity, however not yet fully implemented. Methods of joint inference allow us to have a better picture of the past and present evolutionary changes since it is possible to use the majority of the information present in population genomics datasets to properly account of demography signal to search for selection. We propose the use of Approximate Bayesian Computation, a simulation-based method, to implement the joint inference of demography and selection parameters in aDNA studies. Traditional ABC approaches are computationally expensive, making its use in some scenarios challenging, particularly those including selection. This has changed with the introduction of random forests (RF) in ABC, which can alleviate the computation requirements. We present this new approach with the analysis of time-series population genomic datasets. The implementation of this approach is straightforward in the case of small sample size and heterogeneous sampling. It also has the potential to be applied in more complex demographic scenarios – cases that has more than one event of population contraction, expansion and admixture.