By 2020, there will be 50 billion devices measuring the heartbeat of the global economy in real-time. Measurements about the economic activity are primarily represented in the form of time-series data. Other types of data such as text, images, voice, video, etc. get transformed into the form of time-series.
Until now, economic researchers have used structural and econometric models for time-series predictions. The performance of these models has been underwhelming. Modern algorithms, such as machine learning and new sources of data have demonstrated strong potential. However, the current machine learning techniques require weeks or months of human expert's time, work only on static datasets and are unable to adapt to unseen changes taking place in the real world.
In this talk, we will demonstrate how AutoML for time-series predictions has the ability to build more sophisticated predictive models in a fraction of the time (and cost) while adapting to a dynamic world.
6:30pm - 7:00pm - ODSC Intro, Pizza & Refreshments
7:00pm - 7:50pm - Talk
7:50pm - 8:00pm - Q&A
8:00pm - 8:30pm - Networking
Dr. Darko Matovski is the CEO of causaLens. The company builds a machine that predicts the global economy in real-time and serves prominent organizations including hedge funds and asset managers. Darko has also worked for cutting edge hedge funds and research institutions. For example, the National Physical Laboratory in London (where Alan Turing worked) and Man Group in London. Darko has a Ph.D. in Machine Learning and an MBA.