AI for sales prediction in an environment with limited historical data
In recent years, a lot of research has been done on Artificial Intelligence (AI) and Machine Learning techniques. This has resulted in many available models and open-source code that can be used freely. In this project we want to see how AI can be used to better predict future sales for Flemish SMEs.
This allows them to improve their production and capacity planning, but also to optimize purchasing policy and stock management. However, AI usually needs a lot of data to make predictions. While this is not a problem for large companies such as Amazon, Bol.com or Coolblue, this often forms - in addition to model knowledge and IT infrastructure - a major barrier for SMEs to get started with AI.
With ever-increasing globalization, SMEs are fighting with unequal weapons against the competition of multinationals. This research project aims to apply AI techniques to make good sales forecasts, even where there is little data. We want to implement models that exploit the hierarchical (hidden) structure of the data in combination with data-poor models and ensemble methods.
In the business cases, we want the AI model to build domain-specific knowledge through human-in-the-loop learning to develop a combined algorithm.
We want to disseminate the expertise built up with this project in the Business Management expertise center to the business world through publications, projects and further training in the context of Lifelong Learning. Furthermore, this project can contribute to enriching data and AI courses within VIVES, and prepare students for a practical environment that often has little business data available.
This allows them to improve their production and capacity planning, but also to optimize purchasing policy and stock management. However, AI usually needs a lot of data to make predictions. While this is not a problem for large companies such as Amazon, Bol.com or Coolblue, this often forms - in addition to model knowledge and IT infrastructure - a major barrier for SMEs to get started with AI.
With ever-increasing globalization, SMEs are fighting with unequal weapons against the competition of multinationals. This research project aims to apply AI techniques to make good sales forecasts, even where there is little data. We want to implement models that exploit the hierarchical (hidden) structure of the data in combination with data-poor models and ensemble methods.
In the business cases, we want the AI model to build domain-specific knowledge through human-in-the-loop learning to develop a combined algorithm.
We want to disseminate the expertise built up with this project in the Business Management expertise center to the business world through publications, projects and further training in the context of Lifelong Learning. Furthermore, this project can contribute to enriching data and AI courses within VIVES, and prepare students for a practical environment that often has little business data available.
01/09/2021 - 31/08/2023
