Highlights to expect at the International Symposium on Forecasting in 2024
Forecasting has always been a crucial business process because it provides the foundations for making informed decisions, optimizing operations, and strategizing for the future. Various techniques have been invented throughout the years to improve the accuracy of forecasts. However, researchers and practitioners would often agree that there has never been a ‘one size fits all’ approach; the most accurate results always depend on the data and the specific problem in hand. While new data driven techniques are invented, improved versions of more ‘traditional’ approaches could still outperform more sophisticated and compute intensive methods, in various scenarios. At the same time, judgmental adjustments of computer-based forecasts, based on solid business logic and information that is not captured in the data, could also be beneficial. And frameworks to monitor the Forecast Value Added (FVA) would also play an important role for the continuous improvement of the forecasting process in an organization.
This is what makes forecasting so exciting. It’s not about one thing to make it successful. It’s about all these aspects that must work in harmony to drive tangible business value. And that’s why I can’t wait to attend the International Symposium on Forecasting (ISF) once again. ISF is the premier forecasting conference, attracting the world’s leading forecasting researchers, practitioners, and students. This year it will take place June 30 – July 3 in Dijon, France. SAS is once again happy to announce that will be sponsoring the event and our forecasting experts from all around the world will be gathering to share key findings from their latest research and from working with our customers and partners to solve challenging forecasting problems.
So, what will the SAS forecasters talk about? Our customer advisory experts will discuss practical applications of how to optimize inventory in manufacturing, forecasting new products using machine learning, and ways to measure the impact of a time series on global accuracy. The talk from our consulting department will focus more on forecasting explainability based on a project that was implemented in one of the largest CPG companies in the world. And finally, our R&D experts will showcase their new two-stage heuristic approach to control forecast bias in demand forecasting and a novel implementation of the Hampel Filter to enhance time series outlier detection performance.
There are numerous other presentations that promise to be engaging at the event. A few that particularly caught my attention are ‘Climate Forecasting: Arctic Sea Ice in Models and Data’, ‘Judgmental adjustments of computer-based forecasts. Are they beneficial? Can they be improved?’, and ‘Navigating Uncertainty: Forecasting Amidst Growing Disruption and Turbulence’. I’m confident it will be an outstanding event filled with thought-provoking presentations and stimulating discussions. Looking forward to seeing you there!
