Optimization for business systems and conversational analytics

State-of-the-art forecasting: Demand planning is a critical part of a businessâ operations. Traditional approaches to forecasting use statistical methods to predict future demand from past transactions, but do not take into account contextual data. However, there are good reasons to believe that contextual data – such as weather, events, product descriptions, sentiment analysis (from reviews, Zendesk tickets, social media), and more – can contribute significant signals that directly influence forecasting accuracy for the better. Additionally, a common problem in demand forecasting is new products introduction since there is no historical data on which to base statistical predictions. Contextual data of related products, as well as their sales history, could be used to infer demand for items sharing similar features.

Faculty Supervisor:

Yoshua Bengio

Student:

Alexandre Marcil

Partner:

Enkidoo Technologies Inc

Discipline:

Computer science

Sector:

Transportation and warehousing

University:

Université de Montréal