Many critical business and societal decisions in areas such as supply chain and healthcare involve numerous potential actions, complex constraints, and goals that can be modeled as objective functions. Mathematical optimization, a core area in Operations Research (OR), provides robust, mathematically grounded methodologies to address such decisions and has shown tremendous benefits in many applications. However, its application requires the creation of accurate and efficient optimization models, necessitating rare expertise and considerable time, creating a barrier to widespread adoption in decision-making. Thus, it is a long-standing goal to make these capabilities widely accessible. The advent of Large Language Models (LLMs) has made advanced Artificial Intelligence (AI) capabilities widely accessible through natural language. LLMs can accelerate expert work in creating formal models like computer programs, and emerging research indicates they can also speed up the development of optimization models by OR experts. We, therefore, propose integrating and advancing LLM and optimization modeling to empower organizational decision-makers to model and solve such complex problems without requiring deep expertise in optimization. In this work, we present our vision for democratizing optimization modeling for organizational decision-making by such a combination of LLMs and optimization modeling. We identify a set of fundamental requirements for the vision's implementation and describe the state of the art through a literature survey and some experimentation. We show that a) LLMs already provide substantial novel capabilities relevant to realizing this vision, but that b) major research challenges remain to be addressed. We also propose possible research directions to overcome these gaps. We would like this work to serve as a call to action to bring together the LLM and OR optimization modeling communities to pursue this vision, thereby enabling much more widespread improved decision-making and increasing by orders of magnitude the benefits AI and OR can bring to enterprises and society.

Trading networks are an indispensable part of today's economy, but to compete successfully with others, they must be efficient in maximizing the value they provide to the external market. While the prior work relies on truthful disclosure of private information to achieve efficiency, we study the problem of designing mechanisms that result in efficient trading networks by incentivizing firms to truthfully reveal their private information to a third party. Additional desirable properties of such mechanisms are weak budget balance (WBB; the third party needs not invest) and individual rationality (IR; firms get non-negative utility). Unlike combinatorial auctions, there may not exist mechanisms that simultaneously satisfy these properties ex post for trading networks. We propose an approach for computing or learning truthful and efficient mechanisms for given networks in a Bayesian setting, where WBB and IR, respectively, are relaxed to ex ante and interim for a given distribution over the private information. We incorporate techniques to reduce computational and sample complexity. We empirically demonstrate that the proposed approach successfully finds the mechanisms with the relaxed properties for trading networks where achieving ex post properties is impossible.

Mathematical decision-optimization (DO) models provide decision support in a wide range of scenarios. Often, hard-to-model constraints and objectives are learned from data. Learning, however, can give rise to DO models that fail to capture the real system, leading to poor recommendations. We introduce an open-source framework designed for large-scale testing and solution quality analysis of DO model learning algorithms. Our framework produces multiple optimization problems at random, feeds them to the user's algorithm and collects its predicted optima. By comparing predictions against the ground truth, our framework delivers a comprehensive prediction profile of the algorithm. Thus, it provides a playground for researchers and data scientists to develop, test, and tune their DO model learning algorithms. Our contributions include: (1) an open-source testing framework implementation, (2) a novel way to generate DO ground truth, and (3) a first-of-its-kind, generic, cloud-distributed Ray and Rayvens architecture. We demonstrate the use of our testing framework on two open-source DO model learning algorithms.

The creation of Bayesian networks often requires the specification of a large number of parameters, making it highly desirable to be able to learn these parameters from historical data. In many cases, such data has uncertainty associated with it, including cases in which this data comes from unstructured analysis or from sensors. When creating diagnosis networks, for example, unstructured analysis algorithms can be run on the historical text descriptions or images of previous cases so as to extract data for learning Bayesian network parameters, but such derived data has inherent uncertainty associated with it due to the nature of such algorithms. Because of the inability of current Bayesian network parameter learning algorithms to incorporate such uncertainty, common approaches either ignore this uncertainty, thus reducing the resulting accuracy, or completely disregard such data. We present an approach for learning Bayesian network parameters that explicitly incorporates such uncertainty, and which is a natural extension of the Bayesian network formalism. We present a generalization of the Expectation Maximization parameter learning algorithm that enables it to handle any historical data with likelihood-evidence-based uncertainty, as well as an empirical validation demonstrating the improved accuracy and convergence enabled by our approach. We also prove that our extended algorithm maintains the convergence and correctness properties of the original EM algorithm, while explicitly incorporating data uncertainty in the learning process.

There is a growing need for systems that react automatically to events. While some events are generated externally and deliver data across distributed systems, others need to be derived by the system itself based on available information. Event derivation is hampered by uncertainty attributed to causes such as unreliable data sources or the inability to determine with certainty whether an event has actually occurred, given available information. Two main challenges exist when designing a solution for event derivation under uncertainty. First, event derivation should scale under heavy loads of incoming events. Second, the associated probabilities must be correctly captured and represented. We present a solution to both problems by introducing a novel generic and formal mechanism and framework for managing event derivation under uncertainty. We also provide empirical evidence demonstrating the scalability and accuracy of our approach.

Efficiency is critical to the profitability of software maintenance and support organizations. Managing such organizations effectively requires suitable measures of efficiency that are sensitive enough to detect significant changes, and accurate and timely in detecting them. Mean time to close problem reports is the most commonly used efficiency measure, but its suitability has not been evaluated carefully. We performed such an evaluation by mining and analyzing many years of support data on multiple IBM products. Our preliminary results suggest that the mean is less sensitive and accurate than another measure, percentiles, in cases that are particularly important in the maintenance and support domain. Using percentiles, we also identified statistical techniques to detect efficiency trends and evaluated their accuracy. Although preliminary, these results may have significant ramifications for effectively measuring and improving software maintenance and support processes.

In many security-related contexts, a quick recognition of security hazards is required. Such recognition is challenging, since available information sources are often insufficient to infer the occurrence of hazards with certainty. This requires that the recognition of security hazard is carried out using inference based on patterns of occurrences distributed over space and time. The two main existing approaches to the inference of security hazards are a) custom-coded solutions, which are tailored to specific patterns, and cannot respond quickly to changes in the patterns of occurrences used for inference, and b) approaches based on direct statistical inferencing techniques, such as regression, which do not enable combining various kinds of evidence regarding the same hazard. In this work, we introduce a more generic formal framework which overcomes the aforementioned deficiencies, together with a case study illustrating the detection of DoS attacks.