Abstract: Forecasting is used in virtually every industry, in scenarios such as sales/demand forecasting, supply chain management, marketing campaign analysis, predictive maintenance, and social media analysis. While forecasting is sometimes neglected during discussions around machine learning, it can in fact benefit hugely from a machine learning approach, and new techniques have recently been developed to greatly improve its accuracy and efficiency.
This talk will provide an overview of a range of common industry use cases for forecasting, including technical deployment scenarios. A high-level technical introduction to the fundamentals of time series forecasting will also be provided, covering typical data requirements, available approaches for modeling and machine learning, and model deployment and operationalization. Finally, some of the latest developments from the forefront of forecasting research will be presented, which promise to increase both the accuracy of forecast models, and their accessibility to a wider range of ""citizen data scientists"", thus having major impact on the way forecasting is conducted in industry.
Bio: Dr. Daniel Parton leads the data science practice at the analytics consultancy, Bardess. He has a background in academia, including a PhD in computational biophysics from the University of Oxford, and previously worked in marketing analytics at Omnicom. He brings both technical and management experience to his role of leading cross-functional data analytics teams, and has led successful and impactful projects for companies in finance, retail, tech, media, manufacturing, pharma and sports/entertainment industries.