Computational Management Science最新文献

In order to characterize non-linear system dynamics and to generate term structures of joint distributions, we propose a flexible and multidimensional approach, which exploits Wasserstein barycentric coordinates for histograms. We apply this methodology to study the relationships between the performance in the European market of the renewable energy sector and that of the fossil fuel energy one. Our methodology allows us to estimate the term structure of conditional joint distributions. This optimal barycentric interpolation can be interpreted as a posterior version of the joint distribution with respect to the prior contained in the past histograms history. Once the underlying dynamics mechanism among the set of variables are obtained as optimal Wasserstein barycentric coordinates, the learned dynamic rules can be used to generate term structures of joint distributions.

This paper studies a prediction problem using time series data and machine learning algorithms. The case study is related to the quality control of bumper beams in the automotive industry. These parts are milled during the production process, and the locations of the milled holes are subject to strict tolerance limits. Machine learning models are used to predict the location of milled holes in the next beam. By doing so, tolerance violations are detected at an early stage, and the production flow can be improved. A standard neural network, a long short term memory network (LSTM), and random forest algorithms are implemented and trained with historical data, including a time series of previous product measurements. Experiments indicate that all models have similar predictive capabilities with a slight dominance for the LSTM and random forest. The results show that some holes can be predicted with good quality, and the predictions can be used to improve the quality control process. However, other holes show poor results and support the claim that real data problems are challenged by inappropriate information or a lack of relevant information.

We present an optimization problem to determine the minimum capital requirement for a non-life insurance company. The optimization problem imposes a non-positive Conditional Value-at-Risk (CVaR) of the insurer's net loss and a portfolio performance constraint. When expressing the optimization problem in a semiparametric form, we demonstrate its convexity for any integrable random variable representing the insurer's liability. Furthermore, we prove that the function defining the CVaR constraint in the semiparametric formulation is continuously differentiable when the insurer's liability has a continuous distribution. We use the Kelley-Cheney-Goldstein algorithm to solve the optimization problem in the semiparametric form and show its convergence. An empirical analysis is carried out by assuming three different liability distributions: a lognormal distribution, a gamma distribution, and a mixture of Erlang distributions with a common scale parameter. The numerical experiments show that the choice of the liability distribution plays a crucial role since marked differences emerge when comparing the mixture distribution with the other two distributions. In particular, the mixture distribution describes better the right tail of the empirical distribution of liabilities with respect to the other two distributions and implies higher capital requirements and different assets in the optimal portfolios.

Hydrogen is considered a solution to decarbonize the transportation sector, an important step to meet the requirements of the Paris agreement. Even though hydrogen demand is expected to increase over the next years, the exact demand level over time remains a main source of uncertainty. We study the problem of where and when to locate hydrogen production plants to satisfy uncertain future customer demand. We formulate our problem as a two-stage stochastic multi-period facility location and capacity expansion problem. The first-stage decisions are related to the location and initial capacity of the production plants and have to be taken before customer demand is known. They involve selecting a modular capacity with a piecewise linear, convex short-term cost function for the chosen capacity level. In the second stage, decisions regarding capacity expansion and demand allocation are taken. Given the complexity of the formulation, we solve the problem using a Lagrangian decomposition heuristic. Our method is capable of finding solutions of sufficiently high quality within a few hours, even for instances too large for commercial solvers. We apply our model to a case from Norway and design the corresponding hydrogen infrastructure for the transportation sector.