A key challenge in inventory management is to identify policies that optimally replenish inventory from multiple suppliers. To solve such optimization problems, inventory managers need to decide what quantities to order from each supplier given the net inventory and outstanding orders so that the expected backlogging, holding, and sourcing costs are jointly minimized. Inventory management problems have been studied extensively for more than 60 years, and yet even basic dual-sourcing problems, in which orders from an expensive supplier arrive faster than orders from a regular supplier, remain intractable in their general form. In addition, there is an emerging need to develop proactive, scalable optimization algorithms that can adjust their recommendations to dynamic demand shifts in a timely fashion. In this work, we approach dual sourcing from a neural network–based optimization lens and incorporate information on inventory dynamics and its replenishment (i.e., control) policies into the design of recurrent neural networks. We show that the proposed neural network controllers (NNCs) are able to learn near-optimal policies of commonly used instances within a few minutes of CPU time on a regular personal computer. To demonstrate the versatility of NNCs, we also show that they can control inventory dynamics with empirical, nonstationary demand distributions that are challenging to tackle effectively using alternative, state-of-the-art approaches. Our work shows that high-quality solutions of complex inventory management problems with nonstationary demand can be obtained with deep neural network optimization approaches that directly account for inventory dynamics in their optimization process. As such, our research opens up new ways of efficiently managing complex, high-dimensional inventory dynamics. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: This work was supported by Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (NCCR Automation) [Grant P2EZP2 191888] and the Army Research Office [Grant W911NF-23-1-0129]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0136 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0136 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

The pervasiveness of Internet of Things results in vast volumes of personal data generated by smart devices of users (data producers) such as smart phones, wearables and other embedded sensors. It is a common requirement, especially for Big Data analytics systems, to transfer these large in scale and distributed data to centralized computational systems for analysis. Nevertheless, third parties that run and manage these systems (data consumers) do not always guarantee users’ privacy. Their primary interest is to improve utility that is usually a metric related to the performance, costs and the quality of service. There are several techniques that mask user-generated data to ensure privacy, e.g. differential privacy. Setting up a process for masking data, referred to in this paper as a ‘privacy setting’, decreases on the one hand the utility of data analytics, while, on the other hand, increases privacy. This paper studies parameterizations of privacy settings that regulate the trade-off between maximum utility, minimum privacy and minimum utility, maximum privacy, where utility refers to the accuracy in the estimations of aggregation functions. Privacy settings can be universally applied as system-wide parameterizations and policies (homogeneous data sharing). Nonetheless they can also be applied autonomously by each user or decided under the influence of (monetary) incentives (heterogeneous data sharing). This latter diversity in data sharing by informational self-determination plays a key role on the privacy-utility trajectories as shown in this paper both theoretically and empirically. A generic and novel computational framework is introduced for measuring privacy-utility trade-offs and their Pareto optimization. The framework computes a broad spectrum of such trade-offs that form privacy-utility trajectories under homogeneous and heterogeneous data sharing. The practical use of the framework is experimentally evaluated using real-world data from a Smart Grid pilot project in which energy consumers protect their privacy by regulating the quality of the shared power demand data, while utility companies make accurate estimations of the aggregate load in the network to manage the power grid. Over 20,000 differential privacy settings are applied to shape the computational trajectories that in turn provide a vast potential for data consumers and producers to participate in viable participatory data sharing systems.

The Internet of Things equips citizens with a phenomenal new means for online participation in sharing economies. When agents self-determine options from which they choose, for instance, their resource consumption and production, while these choices have a collective systemwide impact, optimal decision-making turns into a combinatorial optimization problem known as NP-hard. In such challenging computational problems, centrally managed (deep) learning systems often require personal data with implications on privacy and citizens’ autonomy. This article envisions an alternative unsupervised and decentralized collective learning approach that preserves privacy, autonomy, and participation of multi-agent systems self-organized into a hierarchical tree structure. Remote interactions orchestrate a highly efficient process for decentralized collective learning . This disruptive concept is realized by I-EPOS, the Iterative Economic Planning and Optimized Selections , accompanied by a paradigmatic software artifact. Strikingly, I-EPOS outperforms related algorithms that involve non-local brute-force operations or exchange full information. This article contributes new experimental findings about the influence of network topology and planning on learning efficiency as well as findings on techno-socio-economic tradeoffs and global optimality. Experimental evaluation with real-world data from energy and bike sharing pilots demonstrates the grand potential of collective learning to design ethically and socially responsible participatory sharing economies.