Schedule: Financial Services sessions

Francesca Lazzeri and Jen Ren 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. Read more.

Financial services are increasingly deploying AI services for a wide range of applications, such as identifying fraud and financial crimes. Such deployment requires models to be interpretable, explainable, and resilient to adversarial attacks—regulatory requirements prohibit black-box machine learning models. Jari Koister shares tools and infrastructure has developed to support these needs. Read more.

Quantitative finance is a rich field in finance where advanced mathematical and statistical techniques are employed by both sell-side and buy-side institutions. Chakri Cherukuri explains how machine learning and deep learning techniques are being used in quantitative finance and details how these models work under the hood. Read more.

How efficient is your data platform? The single metric Intuit uses is time to reliable insights: the total of time spent to ingest, transform, catalog, analyze, and publish. Sandeep Uttamchandani shares three design patterns/frameworks Intuit implemented to deal with three challenges to determining time to reliable insights: time to discover, time to catalog, and time to debug for data quality. Read more.

Time series forecasting techniques are applied in a wide range of scientific disciplines, business scenarios, and policy settings. Jeffrey Yau discusses the applications of statistical time series models, such as ARIMA, VAR, and regime-switching models, and machine learning models, such as random forest and neural network-based models, to forecasting problems. Read more.

Production ML applications benefit from reproducible, automated retraining, and deployment of ever-more predictive models trained on ever-increasing amounts of data. Kelley Rivoire explains how Stripe built a flexible API for training machine learning models that's used to train thousands of models per week on Kubernetes, supporting automated deployment of new models with improved performance. Read more.

Data—in part, harvested personal data—brings industries unprecedented insights about customer behavior. We know more about our customers and neighbors than at any other time in history, but we need to avoid crossing the "creepy" line. Nick Curcuru discusses how ethical behavior drives trust, especially in today's IoT age. Read more.

The PayPal data ecosystem is large, with 250+ PB of data transacting in 200+ countries. Given this massive scale and complexity, discovering and access to the right datasets in a frictionless environment is a challenge. Subhadra Tatavarti and Chen Kovacs explain how PayPal’s data platform team is helping solve this problem with a combination of self-service integrated and interoperable products. Read more.

Deep learning using sequence-to-sequence networks (Seq2Seq) has demonstrated unparalleled success in neural machine translation. A less explored but highly sought-after area of forecasting can leverage recent gains made in Seq2Seq networks. Aashish Sheshadri explains how PayPal has applied deep networks to monitoring and alerting intelligence. Read more.

What happens when you have a data science organization but no data engineering organization? Jesse Anderson and Thomas Goolsby explain what happened at USAA without data engineering, how they fixed it, and the results since. Read more.

As a customer-facing fintech company, Earnin has access to various types of valuable customer data, from bank transactions to GPS location. Ji Peng shares how Earnin uses unique datasets to build machine learning models and navigates the challenges of prioritizing and applying machine learning in the fintech domain. Read more.