Adaptive multi-horizon models for probabilistic demand forecasting

This project aims to develop an itinerary demand forecasting model that can handle long-term and short-term forecasting and adjust its parameters under changing situations. General long-term prediction models are relatively precise because the context often remains stationary over time, but can not quickly adapt to unforeseen events, like the global pandemics. It is necessary to develop an adaptive model with multi-horizon perspectives. The model will integrate external data sources to output a plausible range of future booking status.

Combination of multi-horizon models for demand forecasting

This project aims to develop a retail demand forecasting model that can both handle the long-term and short-term forecasting, and adjust its parameters as more data come in. General long-term prediction models are relatively precise because the context often remains same over time, but can not quickly adapt to unforeseen events, like the global pandemics. It is then necessary to develop model with multi-horizon perspectives. With the understanding and results achieved by this project, accurate and real-time improvement solutions could be proposed and implemented.

Modelling consumer choice processes in a dynamic and competitive environment

A “choice model” is a mathematical tool that can be used to anticipate the behaviour of economic agents when they must choose among several options. We will use this technique to predict airline or railway passenger choices as a means of anticipating demand and optimizing supply with regard to availability and ticket prices. As part of this internship, the intern will develop new models and test their performance using actual data.