Hong Kong Machine Learning Season 4 Episode 1

15.09.2021 - Hong Kong Machine Learning - ~3 Minutes

When?

Wednesday, September 15, 2021 from 7:00 PM to 9:00 PM (Hong Kong Time)

Where?

At your home, on zoom. All meetups will be online as long as this COVID-19 crisis is not over.

Programme:

Talk 0: A quick retrospective on the first 3 years of the Hong Kong Machine Learning Meetup

Gautier’s slides

Talk 1: Introduction to Darwinex by its CEO, Juan Colón

Darwinex is a Multi-Asset Broker and Asset Manager, regulated by the Financial Conduct Authority (FCA) in the United Kingdom (FRN 586466). It gives traders the Brokerage Venue to trade the markets, and the Regulatory Cover to attract and monetize 3rd-party investor capital. Darwinex is probably the fastest way for talented traders to attract and manage investor capital at minimum cost and without any regulatory and administrative hurdles. Founded in 2012, Darwinex employs 50+ people across its London headquarters and its development office in Madrid, Spain. It is founder-led, well backed and organically profitable.

For more information: info@darwinex.com +44 20 3769 1554 website

Juan’s slides

Darwinex is sponsoring the Hong Kong Machine Learning Meetups for 2021 H2.

Talk 2: Using 10-K and NLP for investment strategies

by Lucas Krenn (MSc University of Toronto, junior quantitative researcher)

Lucas Krenn is explaining how one can use 10-K corporate filings to design systematic trading strategies on US equities.

Lucas has worked with Komei Ogiyama from HKML EduTech on this project.

Talk 3: FastSHAP: Real-Time Shapley Value Estimation

by Ian Covert (PhD student in the Paul G. Allen School of Computer Science & Engineering at the University of Washington)

Abstract:

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned explainer model. FastSHAP amortizes the cost of explaining many inputs via a learning approach inspired by the Shapley value’s weighted least squares characterization, and it can be trained using standard stochastic gradient optimization. We compare FastSHAP to existing estimation approaches, revealing that it generates high-quality explanations with orders of magnitude speedup.

paper: https://arxiv.org/abs/2107.07436
GitHub (PyTorch implementation): https://github.com/iancovert/fastshap
GitHub (TensorFlow implementation): https://github.com/neiljethani/fastshap

Ian’s home page

Ian’s slides

Video Recording of the HKML Meetup on YouTube

YouTube videos:

Thanks to Darwinex for sponsoring this meetup!

Thanks to our patrons for supporting the meetup!

Check the patreon page to join the current list:

Tomas Thornquist

Season 4
machine learning