MAP segmentation in Bayesian hidden Markov models: a case study

We consider the problem of estimating the maximum posterior probability (MAP) state sequence for a finite state and finite emission alphabet hidden Markov model (HMM) in the Bayesian setup, where both emission and transition matrices have Dirichlet priors. We study a training set consisting of thousands of protein alignment pairs. The training data is used to set the prior hyperparameters for Bayesian MAP segmentation. Since the Viterbi algorithm is not applicable any more, there is no simple procedure to find the MAP path, and several iterative algorithms are considered and compared. The main goal of the paper is to test the Bayesian setup against the frequentist one, where the parameters of HMM are estimated using the training data.     

Risk management in public procurement for innovation: the case of Nordic–Baltic Sea cities

State support for innovation in enterprises has been long-standing. One of the specific support measures is public procurement for innovation, which has only recently re-emerged in academic discussion as well as in the European policy discourse. While the spillovers from this type of innovation policy measure may be substantial, the complex processes underlying the support for innovation through public procurement are associated with high risks. We take an exploratory approach to determine the state of practice of risk management in public procurement for innovation at the local level. Five case studies, which were selected as representative cases of the Nordic–Baltic Sea region in Europe, were analyzed. We found that the cities were, for the most part, actively involved in risk identification; the risks are primarily being met with mixed contracting strategies rather than comprehensive risk management tools.     

Quo vadis public procurement of innovation?

Governments are actively looking for ways to use public procurement so that it would become more effective in facilitating innovation across public and private sectors. However, a shift towards public procurement of innovation (PPI) has proven to be difficult. Whereas the contemporary debate has mostly focused on how to reduce the barriers of PPI through re-conceptualizing the procurement process, there is a need to take into account also wider strategic factors through which governments create capacity to undertake PPI. By revisiting historic and contemporary policy initiatives, four strategies for the future can be envisioned: PPI as experimental innovation policy, from fiscal policy under austerity to PPI, mission-oriented PPI and shifts in administrative culture towards PPI. Each of the strategies demands different capacities from the entrepreneurial sector, as well as state, policy and administrative capacities from the public sector. These issues should be an inherent part of future policy-making and offer new avenues for PPI-related policy analysis and academic research.