In this work we focus on multi-state systems modeled by means of a particular class of non-homogeneous Markov processes introduced in [37], called drifting Markov processes. The main idea behind this type of processes is to consider a non-homogeneity that is "smooth", of a known shape. More precisely, the Markov transition matrix is assumed to be a linear (polynomial) function of two (several) Markov transition matrices. For this class of systems, we first obtain explicit expressions for reliability/survival indicators of drifting Markov models, like reliability, availability, maintainability and failure rates. Then, under different statistical settings, we estimate the parameters of the model, obtain plug-in estimators of the associated reliability/survival indicators and investigate the consistency of the estimators. The quality of the proposed estimators and the model validation is illustrated through numerical experiments.In this work we focus on multi-state systems (MSS) modeled by means of particular class of non-homogeneous Markov processes introduced in [37], called drifting Markov processes. More specifically, we consider systems with a finite number of states, say s states, {1, . . . , s}. These different states of such a system usually represent different levels of performance.For instance, state "1" can be seen as being associated with the nominal performance of the system, state "s" can be seen as being associated with the total failure, while the other states have intermediate performance levels.Let us denote by α = (α(1), . . . , α(s)) the initial distribution of the chain, that is the distribution of X 0 , α(u) = P(X 0 = u) for any state u ∈ E.The following result, although straightforward, will be useful in the sequel.Lemma 1 For a linear drifting Markov chain and k 1 ≤ k 2 , k 1 , k 2 ∈ N, we have P(X k2 = j | X k1−1 = i) = k2 l=k1 Π l n (i, j).