Put AI to Work
April 15-18, 2019
New York, NY

Forecasting financial time series with deep learning on Azure (Day 2)

Francesca Lazzeri (Microsoft)
Location: Regent
Secondary topics:  Deep Learning and Machine Learning tools, Financial Services, Models and Methods, Temporal data and time-series

Who is this presentation for?

You are a data scientist, software developer, data engineer, or financial data analyst, who wants to use Azure platform and Azure Machine Learning services for machine learning and building financial time series forecasts.

Prerequisite knowledge

  • Experience coding in Python o A basic understanding of machine learning and deep learning topics and terminology
  • Familiarity with Time Series Forecast (useful but not required)

What you'll learn

  • Set up your development environment
  • Access and examine the data
  • Train long short-term memory (LSTM) networks to generate stock market predictions
  • Review training results and register the best model
  • Set up your testing environment
  • Retrieve the model from your workspace
  • Test the model locally
  • Deploy the model
  • Test the deployed model

Description

Francesca Lazzeri will walk you through the core steps for using Azure Machine Learning services to train your machine learning models both locally and on remote compute resources. You will use the training and deployment workflow for Azure Machine Learning service in a Python Jupyter notebook. You can then use the notebook as a template to train your own machine learning model with your own data.

Specifically, this tutorial will show how to generate stock market predictions with long short-term memory (LSTM) networks: LSTM models can use the history of a sequence of data and correctly predict what the future elements of the sequence are going to be. This is very helpful in many different financial use cases, for example, when you need to model stock prices correctly. Finally, you will learn how to deploy the model as a web service in Azure Container Instances (ACI). A web service is an image, in this case a Docker image, that encapsulates the scoring logic and the model itself. Each topic will include a lecture combined with hands-on exercises.

Agenda

  1. Introduction to Time Series Forecast
  2. Introduction to Neural Networks for Time Series Forecast
  3. Azure Machine Learning Services
  4. Applied Use Case: Stock Market Predictions with LSTMs
Photo of Francesca Lazzeri

Francesca Lazzeri

Microsoft

Francesca Lazzeri is a senior machine learning scientist at Microsoft on the cloud advocacy team and an expert in big data technology innovations and the applications of machine learning-based solutions to real-world problems. Her research has spanned the areas of machine learning, statistical modeling, time series econometrics and forecasting, and a range of industries—energy, oil and gas, retail, aerospace, healthcare, and professional services. Previously, she was a research fellow in business economics at Harvard Business School, where she performed statistical and econometric analysis within the technology and operations management unit. At Harvard, she worked on multiple patent, publication and social network data-driven projects to investigate and measure the impact of external knowledge networks on companies’ competitiveness and innovation. Francesca periodically teaches applied analytics and machine learning classes at universities and research institutions around the world. She’s a data science mentor for PhD and postdoc students at the Massachusetts Institute of Technology and speaker at academic and industry conferences—where she shares her knowledge and passion for AI, machine learning, and coding.