04-27, 11:00–11:45 (America/Los_Angeles), St. Helens
Join us as we take a deep dive into the intricacies of our design process toward creating a demand simulator in Python. In this talk, we will discuss our modeling choices for both the demand and the market. We will also share how developing a simulator can help understand how models learn and adapt to changing realities and conditions.
The demand simulator has been essential in our efforts to continuously improve our strategies and provide the best demand forecasting models. Staying competitive in a tough market requires conducting research, and we hope to inspire others by showing what can be achieved.
In this talk, we will briefly discuss the importance of providing accurate demand forecasting and price optimization for businesses today. We will highlight its role in helping make informed decisions about production, inventory, and pricing. The main focus of the talk will be the design of a Demand Simulator and how its ability to simulate market conditions can be beneficial when evaluating the performance of pricing models. We’ll go into depth regarding the mathematical formulations we used to formalize the problem in its entirety. We’ll also walk you through our development thought process and the most important tools we used.
Obtaining risk-free scenarios to test demand forecasting models such as your scikit-learn or XGBoost models and analyze your solutions may sound too good to be true, but it is achievable. Join us to learn how a demand simulation tool can be an invaluable resource for experimenting with new ideas and continuously improving pricing strategies.
Previous knowledge expected
Pablo is a renowned Machine Learning Engineer with over 15 years of experience in the energy, meteorology, and retail industries. He currently leads technical matters in forecasting and pricing initiatives at Tryolabs, skillfully driving cloud-based ML solutions for a multi-million dollar e-commerce business.
In his dual role at Tryolabs, Pablo provides expert client-facing consultancy services and leads the pricing-squad in creating cutting-edge solutions such as the Market Simulation tool, which is crucial for developing pricing-core, a custom-made pricing solution offering unparalleled value to clients.
Throughout his career, Pablo has implemented Uruguay's National Meteorological Databank and its management software, designed and implemented calculations for meteorological products derived from raw observations, and contributed to the development of Uruguay's National Power System Optimization software, SimSEE. Pablo's deeply analytical mindset and dedication to producing actionable data have made a lasting impact across industries, driving data-driven decision-making processes.