5th OJA Forum: How can online job advertisements help to predict the demand for skills? – Part 4
In this blog series, international experts present their work on predicting the demand for skills using online job advertisements (OJAs). They explain whether and to what extent skills can currently be predicted by using OJAs and address opportunities and challenges. One of these experts is Wyatt Clarke. As a Research Economist at IBM Research, he conducts research on how deep learning architectures can help to accurately predict skills in OJAs.
Probing the limits of skill demand forecasting
At the 5th OJA Forum of the Bertelsmann Stiftung and the Federal Institute for Vocational Education and Training, Wyatt Clarke from IBM Research discussed potential limits of forecasting the skill demand. His research group has applied deep learning architectures to precisely predict future mentions of skills in online job advertisements. In the video, Wyatt Clarke discusses what they have learned about when skill forecasting is useful, how much deep learning can improve forecasts, and implementation challenges of maintaining indices of future skill demand for many skills.
Weitere Beiträge zum „5th OJA Forum“: