Conference Agenda

Python and its vast ecosystem are great for data pre-processing, solution analysis, and visualization, but Python’s design as a general-purpose programming language makes it less than ideal for expressing the complex optimization problems typical of prescriptive analytics. AMPL is a declarative language that is designed for describing optimization problems and that integrates naturally with Python.

In this presentation, you’ll learn how the combination of AMPL modeling with Python environments and tools has made optimization software more natural to use, faster to run, and easier to integrate with enterprise systems. We will show how AMPL and Python work together in a range of contexts:

- Installing AMPL and solvers as Python packages anywhere

- Fast data transfer from/to Python data structures such as Pandas and Polars dataframes

- Deploying models to the cloud quickly and easily

You’ll also see how generative AI technology is enabling a rapid development process for both AMPL and Python, reducing the time and effort to produce a working application that’s ready for end-users.

Machine learning has become a prevalent tool for providing predictive models in many applications. We are interested in using such predictors to model relationships between variables of an optimization model in Gurobi. The Gurobi Machine Learning Python package makes it easy to insert regression models trained by popular frameworks (e.g., scikit-learn, Keras, PyTorch, XGBoost, LightGBM) directly into an optimization model. These regression models may be linear or logistic regressions, neural networks, or based on decision trees. In this talk, we will present the functionalities and applications of Gurobi Machine Learning and demonstrate best practice applications.

The field of generative artificial intelligence (GenAI) has seen exponential growth over the past few years in research papers and publications. The techniques have gained traction across industries. A hype train is rolling, and it shows promising research areas for leveraging GenAI in the field of Operations Research: code generation to increase productivity, chatbots for documentation, generation of mathematical optimization models - just to name a few. In this talk we present an experiment which combines LLMs and decision support tools for decision making in FICO Xpress Insight, e.g. to create an optimized pricing strategy.

Large language models (LLMs) frequently produce incorrect or misleading results, a phenomenon commonly called "hallucination". We demonstrate basic examples where a slight adaptation of a question (prompt) turns a previously helpful LLM response into a false statement. Besides such observations of inaccuracies, we need to consider data exposure, data leakage, privacy violations, copyright violations, biased answers, dangerous or unethical usage, inappropriate language and malicious code, and discuss answers to these challenges. Best practices need to be followed to responsibly leverage GenAI in decision support tools!

It is important to balance innovation with risk mitigation when leveraging GenAI for decision-making, and we advocate for a holistic approach that combines technological advancements with ethical considerations and human oversight.