Economic Forecasting with Machine Learning (+ Foray into Deep Learning)

Hosted by Analytics & Data Science by Dataiku NY

Public group


Link to the live stream:

Hi data science enthusiasts,

In this Meetup, two data scientists will present their projects on machine learning and deep learning. Alex Wolf, Data Scientist at Dataiku, will first introduce the translator he developed using a new neural network architecture called the Transformer. Nicolas Woloszko, Junior Economist at OECD, will then present the algorithm he and his team built to make GDP projections for G7 countries, which proved more reliable than the most well-known existing methods.

A Novel Neural Network Architecture for Natural Language Processing:

Deep Learning in NLP has been dominated in the past years by recurrent and convolutional models. But other models emerge to improve translation quality and performance.
Alex has developed a translator for his team and clients using a new neural network architecture called the Transformer. Unlike traditional translator models, this one solely focuses on attention instead of recurrence and develops powerful NLP models in a fraction of the training time.
Alex will explain how he built the translator, give a live demo, and discuss how the Transformer is able to overcome pitfalls of RNN models.

Economic Forecasting with Machine Learning

GDP forecasting for the world’s major economies is no easy task, but introducing machine learning in the field of economic research opens up new possibilities. Nicolas and his team created a forecasting algorithm – dubbed Adaptive-GBT with Predictive Intrapolation (PI) – that is specifically tailored for macroeconomic forecasting, and draws from both existing machine learning techniques and original contributions to the field. He will present their research and discuss the 2018 forecasts, as well as to what extent it can help assess the impact of current macroeconomic policies.

Speakers bios:

Alex Wolf is a Data Scientist at Dataiku, working with clients around the world to organize their data infrastructures and deploy data-driven products into production. Prior to that, he worked on software and business development in the tech industry and studied Computer Science and Statistics at Dartmouth College. He's passionate about the latest developments in Deep Learning/Tech and works at enriching Dataiku's NLP features.

Nicolas Woloszko is a data scientist and an economist. He joined the OECD in September 2016, where he initiated an innovative project that aims at bridging the gap between machine learning and economics. Prior to joining the OECD, Nicolas has spent time in academia and consulting. He has a dual background in economics and applied maths.